Upload Emu3.5 Image FlashAR from ModelScope

README.md

@@ -0,0 +1,48 @@
+---
+license: apache-2.0
+tags: []
+
+#model-type:
+##如 gpt、phi、llama、chatglm、baichuan 等
+#- gpt
+
+#domain:
+##如 nlp、cv、audio、multi-modal
+#- nlp
+
+#language:
+##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
+#- cn 
+
+#metrics:
+##如 CIDEr、Blue、ROUGE 等
+#- CIDEr
+
+#tags:
+##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
+#- pretrained
+
+#tools:
+##如 vllm、fastchat、llamacpp、AdaSeq 等
+#- vllm
+---
+### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
+#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
+
+SDK下载
+```bash
+#安装ModelScope
+pip install modelscope
+```
+```python
+#SDK模型下载
+from modelscope import snapshot_download
+model_dir = snapshot_download('lxazjk/Emu3.5-image-FlashAR')
+```
+Git下载
+```
+#Git模型下载
+git clone https://www.modelscope.cn/lxazjk/Emu3.5-image-FlashAR.git
+```
+
+<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>

ckpts/FlashAR_step74000_geneval077798_cfg5/README.md

@@ -0,0 +1,12 @@
+# FlashAR checkpoint
+
+Checkpoint: `FlashAR_step74000_geneval077798_cfg5`
+
+- Base: Emu3.5-Image FlashAR
+- Training step: 74000
+- GenEval setting: HW=32, CFG=5.0, official detector
+- GenEval overall score: 0.77798
+- Images: 2212
+- Prompts: 553
+
+See `geneval_cfg5_officialdet/summary.txt` for the task breakdown.

ckpts/FlashAR_step74000_geneval077798_cfg5/checkpoint_meta.json

@@ -0,0 +1,6 @@
+{
+  "format": "hf_safetensors",
+  "global_step": 74000,
+  "epoch": 4,
+  "save_reason": "step"
+}

ckpts/FlashAR_step74000_geneval077798_cfg5/config.json

@@ -0,0 +1,111 @@
+{
+  "model_type": "emu3_nar",
+  "architectures": [
+    "EmuNAR"
+  ],
+  "format": "hf_safetensors",
+  "format_version": 1,
+  "base_model_name_or_path": "./weights/Emu3.5-Image",
+  "tokenizer_name_or_path": "./src/tokenizer_emu3_ibq",
+  "vq_model_name_or_path": "./weights/Emu3.5-VisionTokenizer",
+  "torch_dtype": "bf16",
+  "vocab_size": 282926,
+  "hidden_size": 5120,
+  "visual_token_offset": 151854,
+  "use_vertical_block": true,
+  "vertical_layers": 4,
+  "vertical_start_layer": 60,
+  "backbone_config": {
+    "vocab_size": 282926,
+    "max_position_embeddings": 32768,
+    "hidden_size": 5120,
+    "intermediate_size": 25600,
+    "num_hidden_layers": 64,
+    "num_attention_heads": 64,
+    "num_key_value_heads": 8,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "pretraining_tp": 1,
+    "use_cache": false,
+    "rope_theta": 1000000,
+    "rope_scaling": null,
+    "attention_dropout": 0.0,
+    "img_token_id": 151851,
+    "boi_token_id": 151852,
+    "eoi_token_id": 151853,
+    "eol_token_id": 151846,
+    "eof_token_id": 151847,
+    "image_area": 518400,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+      "Emu3ForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 151849,
+    "pad_token_id": 151643,
+    "eos_token_id": 151850,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "./weights/Emu3.5-Image",
+    "_attn_implementation_autoset": true,
+    "transformers_version": "4.51.0",
+    "attention_bias": false,
+    "max_window_layers": 28,
+    "model_type": "Emu3",
+    "sliding_window": 4096,
+    "use_sliding_window": false
+  }
+}

ckpts/FlashAR_step74000_geneval077798_cfg5/geneval_cfg5_officialdet/summary.txt

@@ -0,0 +1,17 @@
+Summary
+=======
+Total images: 2212
+Total prompts: 553
+% correct images: 78.07%
+% correct prompts: 93.13%
+
+Task breakdown
+==============
+position         = 80.75% (323 / 400)
+two_object       = 88.13% (349 / 396)
+counting         = 45.31% (145 / 320)
+colors           = 90.16% (339 / 376)
+single_object    = 98.44% (315 / 320)
+color_attr       = 64.00% (256 / 400)
+
+Overall score (avg. over tasks): 0.77798

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1ea2c8ced5135ea19646adaa8d64da56dd046a5d412ec07fbcb5f53535417a
+size 4952416280

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0b8e956f3ad2e6328c0967c0fe4f9c9a36b60b5129e582f1bcda72c4da280f
+size 4959876792

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767097dd1b4ed79131cb607f3699482412f064c40e76ceabb7ed3d5d162bdf8d
+size 4875989872

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d87405ad255185e22c6a329fc4d0554a20bf56d5ea0144d43ca863a1e30052a
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f4e84784b701e1ccb5e87e38348b7c2c0c4e830348b48c35c8bde4d042788d
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279ff2d0f8d9004c7f0df024913fb20988f342eb0b96ba7dfab17d3723756319
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65cb7341a505454930b12d2e9c15fe5cbbd1bd0af228d3ef43ac5bda9986c911
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12eb1bfb8a876007d550bf518a43b71e1a930ee6ea6f94600801669dad7b75e3
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce42bc98a7dbbf13f44d5d03ff1b25d76a4f26f22a80ac2cffee336bfb59c84
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8fdd11bf8741ec11130f85fdb8d609abf767fca29798f101fc6dde6fc1a911
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72cf5aa58e88c4308e15df98ea3dd6bfd977147529641e76811956c74e812b45
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0942e00640343b6bddc7ef2dcd2291a58edfaf5bda596df5d6db89641f32c94a
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96dab39de01cb2c8698a9c0a32c95e85ae14ded49df33cfcd83cdc3ba7f96165
+size 4875989912

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f63e323a9fea70c0bc5670bdcc94cdac8b7cfc64fcbec3973446b3bd99f9ce
+size 4847568640

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314eef5aa1d587c83f612ccf49e06af6de18a3c1743f034655b426b8a64efbad
+size 3712057288

ckpts/FlashAR_step74000_geneval077798_cfg5/model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c194ef346dd3a909de355f0e0e741b84c6ac8f7b1d8db49589ed8a647dbc255
+size 2910281532

ckpts/FlashAR_step74000_geneval077798_cfg5/model.safetensors.index.json

@@ -0,0 +1,765 @@
+{
+  "metadata": {
+    "total_size": 75017999620
+  },
+  "weight_map": {
+    "backbone.embed_tokens.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.self_attn.q_norm.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.self_attn.k_norm.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.mlp.gate_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.mlp.up_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.mlp.down_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.self_attn.o_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.self_attn.q_norm.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.self_attn.k_norm.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.mlp.gate_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.mlp.up_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.mlp.down_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.input_layernorm.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.1.post_attention_layernorm.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.2.self_attn.q_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.2.self_attn.k_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.2.self_attn.v_proj.weight": "model-00001-of-00016.safetensors",
+    "backbone.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.2.self_attn.q_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.2.self_attn.k_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.2.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.2.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.2.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.2.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.2.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.self_attn.q_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.self_attn.k_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.3.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.self_attn.q_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.self_attn.k_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.4.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.self_attn.q_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.self_attn.k_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.5.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.self_attn.q_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.self_attn.k_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.6.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.7.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.7.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.7.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.7.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.7.self_attn.q_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.7.self_attn.k_norm.weight": "model-00002-of-00016.safetensors",
+    "backbone.layers.7.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.7.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.7.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.7.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.7.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.self_attn.q_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.self_attn.k_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.8.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.self_attn.q_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.self_attn.k_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.9.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.self_attn.q_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.self_attn.k_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.10.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.self_attn.q_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.self_attn.k_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.11.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.12.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.12.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.12.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.12.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.12.self_attn.q_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.12.self_attn.k_norm.weight": "model-00003-of-00016.safetensors",
+    "backbone.layers.12.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.12.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.12.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.12.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.12.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.self_attn.q_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.self_attn.k_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.13.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.self_attn.q_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.self_attn.k_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.14.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.self_attn.q_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.self_attn.k_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.15.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.self_attn.q_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.self_attn.k_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.16.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.17.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.17.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.17.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.17.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.17.self_attn.q_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.17.self_attn.k_norm.weight": "model-00004-of-00016.safetensors",
+    "backbone.layers.17.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.17.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.17.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.17.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.17.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.self_attn.q_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.self_attn.k_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.18.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.self_attn.q_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.self_attn.k_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.19.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.self_attn.q_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.self_attn.k_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.20.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.self_attn.q_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.self_attn.k_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.21.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.22.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.22.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.22.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.22.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.22.self_attn.q_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.22.self_attn.k_norm.weight": "model-00005-of-00016.safetensors",
+    "backbone.layers.22.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.22.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.22.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.22.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.22.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.self_attn.q_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.self_attn.k_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.23.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.self_attn.q_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.self_attn.k_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.24.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.self_attn.q_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.self_attn.k_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.25.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.self_attn.q_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.self_attn.k_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.26.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.27.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.27.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.27.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.27.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.27.self_attn.q_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.27.self_attn.k_norm.weight": "model-00006-of-00016.safetensors",
+    "backbone.layers.27.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.27.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.27.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.27.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.27.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.self_attn.q_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.self_attn.k_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.28.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.self_attn.q_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.self_attn.k_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.29.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.self_attn.q_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.self_attn.k_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.30.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.self_attn.q_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.self_attn.k_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.31.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.32.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.32.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.32.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.32.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.32.self_attn.q_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.32.self_attn.k_norm.weight": "model-00007-of-00016.safetensors",
+    "backbone.layers.32.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.32.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.32.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.32.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.32.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.self_attn.q_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.self_attn.k_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.33.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.self_attn.q_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.self_attn.k_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.34.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.self_attn.q_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.self_attn.k_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.35.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.self_attn.q_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.self_attn.k_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.36.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.37.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.37.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.37.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.37.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.37.self_attn.q_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.37.self_attn.k_norm.weight": "model-00008-of-00016.safetensors",
+    "backbone.layers.37.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.37.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.37.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.37.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.37.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.self_attn.q_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.self_attn.k_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.38.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.self_attn.q_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.self_attn.k_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.39.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.self_attn.q_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.self_attn.k_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.40.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.self_attn.q_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.self_attn.k_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.41.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.42.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.42.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.42.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.42.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.42.self_attn.q_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.42.self_attn.k_norm.weight": "model-00009-of-00016.safetensors",
+    "backbone.layers.42.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.42.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.42.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.42.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.42.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.self_attn.q_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.self_attn.k_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.43.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.self_attn.q_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.self_attn.k_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.44.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.self_attn.q_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.self_attn.k_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.45.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.self_attn.q_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.self_attn.k_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.46.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.47.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.47.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.47.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.47.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.47.self_attn.q_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.47.self_attn.k_norm.weight": "model-00010-of-00016.safetensors",
+    "backbone.layers.47.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.47.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.47.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.47.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.47.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.self_attn.q_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.self_attn.k_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.48.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.self_attn.q_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.self_attn.k_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.49.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.self_attn.q_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.self_attn.k_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.50.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.self_attn.q_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.self_attn.k_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.51.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.52.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.52.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.52.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.52.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.52.self_attn.q_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.52.self_attn.k_norm.weight": "model-00011-of-00016.safetensors",
+    "backbone.layers.52.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.52.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.52.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.52.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.52.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.self_attn.q_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.self_attn.k_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.53.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.self_attn.q_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.self_attn.k_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.54.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.self_attn.q_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.self_attn.k_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.55.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.self_attn.q_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.self_attn.k_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.56.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.57.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.57.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.57.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.57.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.57.self_attn.q_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.57.self_attn.k_norm.weight": "model-00012-of-00016.safetensors",
+    "backbone.layers.57.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.57.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.57.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.57.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.57.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.self_attn.q_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.self_attn.k_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.58.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.self_attn.q_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.self_attn.k_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.59.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.self_attn.q_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.self_attn.k_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.60.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.self_attn.q_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.self_attn.k_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.61.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.62.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.62.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.62.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.62.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.62.self_attn.q_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.62.self_attn.k_norm.weight": "model-00013-of-00016.safetensors",
+    "backbone.layers.62.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.62.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.62.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.62.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.62.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.self_attn.q_norm.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.self_attn.k_norm.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "backbone.layers.63.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "backbone.norm.weight": "model-00014-of-00016.safetensors",
+    "horizontal_head.weight": "model-00014-of-00016.safetensors",
+    "vertical_block.0.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "vertical_block.0.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "vertical_block.0.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "vertical_block.0.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "vertical_block.0.self_attn.q_norm.weight": "model-00014-of-00016.safetensors",
+    "vertical_block.0.self_attn.k_norm.weight": "model-00014-of-00016.safetensors",
+    "vertical_block.0.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.0.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.0.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.0.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.0.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.self_attn.q_norm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.self_attn.k_norm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.1.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.self_attn.q_norm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.self_attn.k_norm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.2.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.self_attn.q_norm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.self_attn.k_norm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "vertical_block.3.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "vertical_norm.weight": "model-00015-of-00016.safetensors",
+    "vertical_head.weight": "model-00016-of-00016.safetensors",
+    "hv_gate_mlp.0.weight": "model-00016-of-00016.safetensors",
+    "hv_gate_mlp.2.weight": "model-00016-of-00016.safetensors",
+    "hv_gate_mlp.2.bias": "model-00016-of-00016.safetensors",
+    "hv_gate_corner.weight": "model-00016-of-00016.safetensors",
+    "hv_gate_corner.bias": "model-00016-of-00016.safetensors"
+  }
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}