Add files using upload-large-folder tool

.gitattributes

@@ -38,3 +38,6 @@ global_step_40/output_hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -tex
 global_step_60/output_hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 global_step_80/output_hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 global_step_100/output_hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_10/output_hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_30/output_hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_50/output_hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

global_step_10/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd35132ce51c27e88ccad1647882248fba41f7782eed5fe71fc0d810ebb8ebd
+size 7316

global_step_10/output_hf_model/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032c971e28e1fb895be5d806ff480d7f19fc1a446286376f3c06897fd0db8cbc
+size 4899120824

global_step_10/output_hf_model/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c71fee16c96b47ed5362ccccf7428dbdf5eef663820ac579e6078e18097886
+size 4969452368

global_step_10/output_hf_model/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36559d09fdc457c6d19e6ece35569e72f35323fb1c092f2e0d88a8e689463fdc
+size 4320358472

global_step_10/output_hf_model/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c271305dbed61564e94704794e083ea5c2d1f696614099ac0dacf578b52153a4
+size 2192585176

global_step_10/output_hf_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

global_step_20/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58fa73ae6711b1f04a2614ab02f8ccfc7833f20c5eb3ebcda0a252129b03aed1
+size 7316

global_step_20/output_hf_model/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1262a677bc5853559c1dd56276cabc7f4f648eb3e1a6f018cff433076634c2
-size 4994559064
+oid sha256:24c8d87407c512ee040449ee24f06d4419bbdbbbffe3d889d91a3628fc05df46
+size 4935878800

global_step_20/output_hf_model/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:379f38685d1355ab6824f77d432651aa363400c29afa4163d0bf5f1227184254
-size 4986175112
+oid sha256:bda3c9e5c2a0988473f931ec0f9c0a5f080472100460ab674717f7ebb64c8916
+size 4949520488

global_step_20/output_hf_model/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca3d3ef69b9fed85d06560f6e43beb81962f27349fc7782d80a3b25f383b819
-size 4999810752
+oid sha256:b7a751f368b6d59a1fbd47cc88f20022deabef119f79217f86e3cbb671a08602
+size 4944177224

global_step_20/output_hf_model/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3af43f1b793a8beca676cd4e63fcde5b161972b534e857f6149c4bcf5ab692
-size 1400971896
+oid sha256:c276669b1ea6b908721196519a1b6a5047c1a896e3de39839443c24f5b3862fd
+size 1551940320

global_step_30/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aff801076a27cd6e9ac10aa01f362e7383e916e1debe8c7ef1162854bdf6a89
+size 7316

global_step_30/output_hf_model/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6a0344ab54aabe4a20ce575d1a058c1fac16468a2a12d22befaffafc985445
+size 4977737248

global_step_30/output_hf_model/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d224a8077f47b2ccd23919cb3f8840aec71162389dd4a03c1919da2467843eb
+size 4999880848

global_step_30/output_hf_model/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32bb7f678a9cf8dc060d980d8d72df3e0bfc0517f76d1fd762bbd94bfb8dd3c
+size 4902275248

global_step_30/output_hf_model/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b06ebbcb15f7e63ff41bcfcb7ee572fdf47e9e770c056e9edb67e5606dda33
+size 1501623496

global_step_30/output_hf_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

global_step_40/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea6db8bd3e471365f2d9bdda93b6c2f69ad3956b2678d348f607e0c11fddcf1
+size 7316

global_step_40/output_hf_model/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056909ceaa2e8363abd7ab78bae14b781d574edb9e304693decf3224293751e3
-size 4994614344
+oid sha256:a5d728cf4bcc450d83648c7f91bbf8bc92e9474a3f14f1d296dc64015c0327b1
+size 4964054264

global_step_40/output_hf_model/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b77d20daf238ff230dc4885b8ce9b03c87114f86ae54d851d182efcf107dcd
-size 4910605072
+oid sha256:f97944260e4d762eb844cf962bcf410088ec72a37203b6773bf4e8454a016f41
+size 4983060688

global_step_40/output_hf_model/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ee8415d2f695ca84332f8519d85a0a97cf0a0e3914ea07065164c4c0a5c70a
-size 4957862624
+oid sha256:fe092d645ceba16a210835e91ce2eb301f4c9933678787d0f9ab1289b8bd205d
+size 4991505864

global_step_40/output_hf_model/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a18e7b3fb5840075ccfd426a42344608f3fdbb89228391e496e6ad8317510d1
-size 1518434736
+oid sha256:0cf901a3b7d2691d84d156bfa36e06b61420f51ba690d4d0ca7d8494e1f5b339
+size 1442895928

global_step_50/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b889d2ba3c70eb5d0d8f0ba47c78ed097be4e7f9ede8891ab40704f21dc2658e
+size 7316

global_step_50/output_hf_model/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:728836c62e181028c3b9cdc86f054fc06bbea93f7555190e1185a0d3ac594a84
+size 1635870968

global_step_50/output_hf_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

global_step_60/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b68431e69450b4712abc1e6bf4974e5356baecc260e165afd5bc8262765eb3
+size 7316

global_step_60/output_hf_model/model.safetensors.index.json

@@ -5,403 +5,403 @@
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00004.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.2.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.28.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.33.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.norm.weight": "model-00003-of-00004.safetensors"
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00001-of-00004.safetensors"
   }
 }

global_step_70/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9df0f334b90b16fc289fb187f0f959dc0ea6828d9d1b08e2d75b9a024743caf
+size 7316

global_step_70/output_hf_model/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

global_step_70/output_hf_model/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

global_step_70/output_hf_model/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

global_step_70/output_hf_model/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

global_step_70/output_hf_model/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00001-of-00004.safetensors"
+  }
+}

global_step_70/output_hf_model/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

global_step_70/output_hf_model/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

global_step_80/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:710f06f24ee1fb0ea522bd225c508ab854c7503cf386d1f5f1338b1f4d9eb1a7
+size 7316

global_step_80/output_hf_model/model.safetensors.index.json

@@ -4,404 +4,404 @@
     "total_size": 16381470720
   },
   "weight_map": {
-    "lm_head.weight": "model-00002-of-00004.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "lm_head.weight": "model-00003-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.0.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.32.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.34.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.34.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.4.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.norm.weight": "model-00003-of-00004.safetensors"
   }
 }

global_step_90/actor/fsdp_config.json

@@ -0,0 +1,4 @@
+{
+    "FSDP_version": 1,
+    "world_size": 4
+}

global_step_90/actor/huggingface/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

global_step_90/actor/huggingface/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

global_step_90/actor/huggingface/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

global_step_90/actor/huggingface/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

global_step_90/actor/huggingface/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

global_step_90/actor/huggingface/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

global_step_90/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02f36fa03850a517cac2c714aca480b046baacd1ea6850577c241804f00896b
+size 7316