Upload folder using huggingface_hub
Browse files- README.md +3 -11
- config.json +1 -1
- model-00001-of-00030.safetensors +2 -2
- model-00002-of-00030.safetensors +2 -2
- model-00003-of-00030.safetensors +2 -2
- model-00004-of-00030.safetensors +2 -2
- model-00005-of-00030.safetensors +2 -2
- model-00006-of-00030.safetensors +2 -2
- model-00007-of-00030.safetensors +2 -2
- model-00008-of-00030.safetensors +2 -2
- model-00009-of-00030.safetensors +2 -2
- model-00010-of-00030.safetensors +2 -2
- model-00011-of-00030.safetensors +2 -2
- model-00012-of-00030.safetensors +2 -2
- model-00013-of-00030.safetensors +2 -2
- model-00014-of-00030.safetensors +2 -2
- model-00015-of-00030.safetensors +2 -2
- model-00016-of-00030.safetensors +2 -2
- model-00017-of-00030.safetensors +2 -2
- model-00018-of-00030.safetensors +2 -2
- model-00019-of-00030.safetensors +2 -2
- model-00020-of-00030.safetensors +2 -2
- model-00021-of-00030.safetensors +2 -2
- model-00022-of-00030.safetensors +2 -2
- model-00023-of-00030.safetensors +2 -2
- model-00024-of-00030.safetensors +2 -2
- model-00025-of-00030.safetensors +2 -2
- model-00026-of-00030.safetensors +2 -2
- model-00027-of-00030.safetensors +2 -2
- model-00028-of-00030.safetensors +2 -2
- model-00029-of-00030.safetensors +2 -2
- model.safetensors.index.json +1 -321
- tokenizer.json +1 -1
- tokenizer_config.json +1 -1
README.md
CHANGED
|
@@ -12,16 +12,8 @@ model_type: llama
|
|
| 12 |
license: llama2
|
| 13 |
---
|
| 14 |
|
| 15 |
-
Sharp Balance is a general capability upgrade to Llama 2
|
| 16 |
|
| 17 |
-
|
| 18 |
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
## Evaluation
|
| 22 |
-
|
| 23 |
-
| Model | Avg | ARC | HS | MMLU | TQA |
|
| 24 |
-
|-----------------------|--------|-------|-------|--------|-------|
|
| 25 |
-
| **Sharp Balance** | 71.36 | 69.28 | 87.59 | 69.51 | 59.05 |
|
| 26 |
-
| Llama 2 | 67.35 | 67.32 | 87.33 | 69.83 | 44.92 |
|
| 27 |
-
| Llama 2 Chat | 66.80 | 64.59 | 85.88 | 63.91 | 52.80 |
|
|
|
|
| 12 |
license: llama2
|
| 13 |
---
|
| 14 |
|
| 15 |
+
Sharp Balance is a general capability upgrade to Llama 2 70b.
|
| 16 |
|
| 17 |
+
It does not have any current practical use. The model is available for legacy and reference purposes. View our profile for our latest models.
|
| 18 |
|
| 19 |
+
The original upload of Sharp Balance contained errors in how weights were saved, which have now been fixed. Additional issues and bugs may be expected; no support is available. Use at your own discretion.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "sequelbox/
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "sequelbox/Llama2-70B-SharpBalance",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
model-00001-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8b33feff49f99a8a8ec673bfb6e360e9401a5892f9fdde86889cc62039b9770
|
| 3 |
+
size 9437317824
|
model-00002-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fddb21c72aaa8b2c948d8c24e3087a5053e1edbca893a63b1f5bee88d6e4b960
|
| 3 |
+
size 9328331680
|
model-00003-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3722c7bbecaffde5b68cbb2854e301608af134d2df614036a6bb52329d75a4c
|
| 3 |
+
size 9932311224
|
model-00004-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72d8d85fd3bc99f82cbc46cea5f311021e6a3c8c3e40df34801f815f7bf11dae
|
| 3 |
+
size 9059830360
|
model-00005-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:343cb478cf714ee410aeb8327098d077aacd4cdb44682075789a36f3cb49be31
|
| 3 |
+
size 9328331704
|
model-00006-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b89325f8dce8ccefcc7a32f2da9730baef79d600bd325cb9bc64f2b61399387b
|
| 3 |
+
size 9328331704
|
model-00007-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd5e7caa9969bc8324f297d84c4476d793f293ba02ea35ebb0085333fbcbb81e
|
| 3 |
+
size 9932311248
|
model-00008-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58d2597e239893c2747d5d3238c3e93a5b774ccca52db1c2c0b8a354069489b2
|
| 3 |
+
size 9059830368
|
model-00009-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e5e66677c863cefe8b07d9c6b98f0233153ec79788e1170e66f140449a28a1a
|
| 3 |
+
size 9328331704
|
model-00010-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f6ad5398e5fe723bc573847b130c2308f23ee01008bf0d539729603fd8dfcf5
|
| 3 |
+
size 9328331704
|
model-00011-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eefa048214f5938b647c190bf9252a2f5359d227b79a4c735b46b86f466e1318
|
| 3 |
+
size 9932311248
|
model-00012-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0190ee23529403fbc5dd3f92262fc8e450338d7cdabc43fe7b2777a99cac8d0e
|
| 3 |
+
size 9059830368
|
model-00013-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec4388c5fbdf4c0c174263990f07801ff43c272def36d889f6ef3ffe9a4591c9
|
| 3 |
+
size 9328331704
|
model-00014-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fdc70efa262a41774b91596dd6acc05ab4067db89502d0fcb6080b1feee2e05
|
| 3 |
+
size 9328331704
|
model-00015-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6606baf426183931df8952f9311839f53fe6f68491e7932dccad08891e032c52
|
| 3 |
+
size 9932311248
|
model-00016-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08942f71e1b74c53f9761e4651c48146be074ac046610559ad283d2515f89164
|
| 3 |
+
size 9059830368
|
model-00017-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84c43da40df9455a68af9d5c37daa302dca8f550a40ef700cb1deb065326a4c6
|
| 3 |
+
size 9328331704
|
model-00018-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96d1aaf08fbaad0da0d0f3c00ddede2f9d371aeac9a00e920d07447678d8a2d4
|
| 3 |
+
size 9328331704
|
model-00019-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ae51479495376ea1cdaca1f0f825b1258b61446ff199ad28248ca18138e0a92
|
| 3 |
+
size 9932311248
|
model-00020-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff137ac8e2e815aa09e5272d9c8a5d9f4b7a784db557f5576338a207d814bb5d
|
| 3 |
+
size 9059830368
|
model-00021-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc725f3b09fb08d0209e04a2a1060761be366937f0919c4543d5eecf9485ba22
|
| 3 |
+
size 9328331704
|
model-00022-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b45a3ef6dfdb03b9ebea89671b859fe932fc552b39eb7e850e6b24eb40f432ec
|
| 3 |
+
size 9328331704
|
model-00023-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acdb978499c71f831bc0f0f1482bcf2a3fd6deb43b44a0f466286a424e0c5b1b
|
| 3 |
+
size 9932311248
|
model-00024-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7312080fb859931a624a64cdef138e1ae10ee84526307b8b7e6243cef93d443
|
| 3 |
+
size 9059830368
|
model-00025-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b47d88c26bced276f0e3600033ed28a6ec8e7b8d348f418d600471b2d0cc3166
|
| 3 |
+
size 9328331704
|
model-00026-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16019e8953525f691852755798dadad02d572001aa6021c5e29a5d8a83b74fad
|
| 3 |
+
size 9328331704
|
model-00027-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e46c512cd2bf746abf38376f30c0cdf3705d51ca2ae484563694c89278dc4e6d
|
| 3 |
+
size 9932311248
|
model-00028-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d126566b0330311b20069aec948f8df4fc5d2e97164314caebbaa6b84582247
|
| 3 |
+
size 9059830368
|
model-00029-of-00030.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b13648deb6775cab8320c57bf7c6c9660969353395f5a02223f0861b160341f
|
| 3 |
+
size 9328331704
|
model.safetensors.index.json
CHANGED
|
@@ -12,11 +12,7 @@
|
|
| 12 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
|
| 13 |
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
|
| 14 |
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
|
| 15 |
-
"model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
|
| 16 |
-
"model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
|
| 17 |
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
|
| 18 |
-
"model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
|
| 19 |
-
"model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
|
| 20 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
|
| 21 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00030.safetensors",
|
| 22 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
|
|
@@ -25,11 +21,7 @@
|
|
| 25 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
|
| 26 |
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
|
| 27 |
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
|
| 28 |
-
"model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
|
| 29 |
-
"model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
|
| 30 |
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
|
| 31 |
-
"model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
|
| 32 |
-
"model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
|
| 33 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
|
| 34 |
"model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 35 |
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
|
|
@@ -38,11 +30,7 @@
|
|
| 38 |
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 39 |
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
|
| 40 |
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
|
| 41 |
-
"model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
|
| 42 |
-
"model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
|
| 43 |
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
|
| 44 |
-
"model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
|
| 45 |
-
"model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
|
| 46 |
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
|
| 47 |
"model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 48 |
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
|
|
@@ -51,11 +39,7 @@
|
|
| 51 |
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 52 |
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
|
| 53 |
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
|
| 54 |
-
"model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
|
| 55 |
-
"model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
|
| 56 |
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
|
| 57 |
-
"model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
|
| 58 |
-
"model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
|
| 59 |
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
|
| 60 |
"model.layers.12.input_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 61 |
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
|
|
@@ -64,11 +48,7 @@
|
|
| 64 |
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 65 |
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
|
| 66 |
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
|
| 67 |
-
"model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
|
| 68 |
-
"model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
|
| 69 |
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
|
| 70 |
-
"model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
|
| 71 |
-
"model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
|
| 72 |
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
|
| 73 |
"model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 74 |
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
|
|
@@ -77,11 +57,7 @@
|
|
| 77 |
"model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 78 |
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
|
| 79 |
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
|
| 80 |
-
"model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
|
| 81 |
-
"model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
|
| 82 |
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
|
| 83 |
-
"model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
|
| 84 |
-
"model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
|
| 85 |
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
|
| 86 |
"model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 87 |
"model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
|
|
@@ -90,11 +66,7 @@
|
|
| 90 |
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 91 |
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
|
| 92 |
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
|
| 93 |
-
"model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
|
| 94 |
-
"model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
|
| 95 |
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
|
| 96 |
-
"model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
|
| 97 |
-
"model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
|
| 98 |
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
|
| 99 |
"model.layers.15.input_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 100 |
"model.layers.15.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
|
|
@@ -103,11 +75,7 @@
|
|
| 103 |
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 104 |
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
|
| 105 |
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
|
| 106 |
-
"model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
|
| 107 |
-
"model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
|
| 108 |
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
|
| 109 |
-
"model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
|
| 110 |
-
"model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
|
| 111 |
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
|
| 112 |
"model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 113 |
"model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
|
|
@@ -116,11 +84,7 @@
|
|
| 116 |
"model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 117 |
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
|
| 118 |
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
|
| 119 |
-
"model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
|
| 120 |
-
"model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
|
| 121 |
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
|
| 122 |
-
"model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
|
| 123 |
-
"model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
|
| 124 |
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
|
| 125 |
"model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 126 |
"model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
|
|
@@ -129,11 +93,7 @@
|
|
| 129 |
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 130 |
"model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
|
| 131 |
"model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
|
| 132 |
-
"model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
|
| 133 |
-
"model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
|
| 134 |
"model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
|
| 135 |
-
"model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
|
| 136 |
-
"model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
|
| 137 |
"model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
|
| 138 |
"model.layers.18.input_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 139 |
"model.layers.18.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
|
|
@@ -142,11 +102,7 @@
|
|
| 142 |
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 143 |
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
|
| 144 |
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
|
| 145 |
-
"model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
|
| 146 |
-
"model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
|
| 147 |
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
|
| 148 |
-
"model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
|
| 149 |
-
"model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
|
| 150 |
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
|
| 151 |
"model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
|
| 152 |
"model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
|
|
@@ -155,11 +111,7 @@
|
|
| 155 |
"model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
|
| 156 |
"model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
|
| 157 |
"model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
|
| 158 |
-
"model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
|
| 159 |
-
"model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
|
| 160 |
"model.layers.19.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
|
| 161 |
-
"model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
|
| 162 |
-
"model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
|
| 163 |
"model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
|
| 164 |
"model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 165 |
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
|
|
@@ -168,11 +120,7 @@
|
|
| 168 |
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 169 |
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
|
| 170 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
|
| 171 |
-
"model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
|
| 172 |
-
"model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
|
| 173 |
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
|
| 174 |
-
"model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
|
| 175 |
-
"model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
|
| 176 |
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
|
| 177 |
"model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
|
| 178 |
"model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
|
|
@@ -181,11 +129,7 @@
|
|
| 181 |
"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
|
| 182 |
"model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
|
| 183 |
"model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
|
| 184 |
-
"model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
|
| 185 |
-
"model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
|
| 186 |
"model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
|
| 187 |
-
"model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
|
| 188 |
-
"model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
|
| 189 |
"model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
|
| 190 |
"model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 191 |
"model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
|
|
@@ -194,11 +138,7 @@
|
|
| 194 |
"model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 195 |
"model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
|
| 196 |
"model.layers.21.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
|
| 197 |
-
"model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
|
| 198 |
-
"model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
|
| 199 |
"model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
|
| 200 |
-
"model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
|
| 201 |
-
"model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
|
| 202 |
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
|
| 203 |
"model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 204 |
"model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
|
|
@@ -207,11 +147,7 @@
|
|
| 207 |
"model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 208 |
"model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
|
| 209 |
"model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
|
| 210 |
-
"model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
|
| 211 |
-
"model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
|
| 212 |
"model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
|
| 213 |
-
"model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
|
| 214 |
-
"model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
|
| 215 |
"model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
|
| 216 |
"model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 217 |
"model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
|
|
@@ -220,11 +156,7 @@
|
|
| 220 |
"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 221 |
"model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
|
| 222 |
"model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
|
| 223 |
-
"model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
|
| 224 |
-
"model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
|
| 225 |
"model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
|
| 226 |
-
"model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
|
| 227 |
-
"model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
|
| 228 |
"model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
|
| 229 |
"model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 230 |
"model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
|
|
@@ -233,11 +165,7 @@
|
|
| 233 |
"model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 234 |
"model.layers.24.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
|
| 235 |
"model.layers.24.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
|
| 236 |
-
"model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
|
| 237 |
-
"model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
|
| 238 |
"model.layers.24.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
|
| 239 |
-
"model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
|
| 240 |
-
"model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
|
| 241 |
"model.layers.24.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
|
| 242 |
"model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 243 |
"model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
|
|
@@ -246,11 +174,7 @@
|
|
| 246 |
"model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 247 |
"model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
|
| 248 |
"model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
|
| 249 |
-
"model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
|
| 250 |
-
"model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
|
| 251 |
"model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
|
| 252 |
-
"model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
|
| 253 |
-
"model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
|
| 254 |
"model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
|
| 255 |
"model.layers.26.input_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 256 |
"model.layers.26.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
|
|
@@ -259,11 +183,7 @@
|
|
| 259 |
"model.layers.26.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 260 |
"model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
|
| 261 |
"model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
|
| 262 |
-
"model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
|
| 263 |
-
"model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
|
| 264 |
"model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
|
| 265 |
-
"model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
|
| 266 |
-
"model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
|
| 267 |
"model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
|
| 268 |
"model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 269 |
"model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
|
|
@@ -272,11 +192,7 @@
|
|
| 272 |
"model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 273 |
"model.layers.27.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
|
| 274 |
"model.layers.27.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
|
| 275 |
-
"model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
|
| 276 |
-
"model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
|
| 277 |
"model.layers.27.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
|
| 278 |
-
"model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
|
| 279 |
-
"model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
|
| 280 |
"model.layers.27.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
|
| 281 |
"model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 282 |
"model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
|
|
@@ -285,11 +201,7 @@
|
|
| 285 |
"model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 286 |
"model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
|
| 287 |
"model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
|
| 288 |
-
"model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
|
| 289 |
-
"model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
|
| 290 |
"model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
|
| 291 |
-
"model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
|
| 292 |
-
"model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
|
| 293 |
"model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
|
| 294 |
"model.layers.29.input_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 295 |
"model.layers.29.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
|
|
@@ -298,11 +210,7 @@
|
|
| 298 |
"model.layers.29.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 299 |
"model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
|
| 300 |
"model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
|
| 301 |
-
"model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
|
| 302 |
-
"model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
|
| 303 |
"model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
|
| 304 |
-
"model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
|
| 305 |
-
"model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
|
| 306 |
"model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
|
| 307 |
"model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 308 |
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
|
|
@@ -311,11 +219,7 @@
|
|
| 311 |
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 312 |
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
|
| 313 |
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
|
| 314 |
-
"model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
|
| 315 |
-
"model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
|
| 316 |
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
|
| 317 |
-
"model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
|
| 318 |
-
"model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
|
| 319 |
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
|
| 320 |
"model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
|
| 321 |
"model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
|
|
@@ -324,11 +228,7 @@
|
|
| 324 |
"model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
|
| 325 |
"model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
|
| 326 |
"model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
|
| 327 |
-
"model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
|
| 328 |
-
"model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
|
| 329 |
"model.layers.30.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
|
| 330 |
-
"model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
|
| 331 |
-
"model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
|
| 332 |
"model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
|
| 333 |
"model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
|
| 334 |
"model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
|
|
@@ -337,11 +237,7 @@
|
|
| 337 |
"model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
|
| 338 |
"model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
|
| 339 |
"model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
|
| 340 |
-
"model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
|
| 341 |
-
"model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
|
| 342 |
"model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
|
| 343 |
-
"model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
|
| 344 |
-
"model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
|
| 345 |
"model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
|
| 346 |
"model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 347 |
"model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
|
|
@@ -350,11 +246,7 @@
|
|
| 350 |
"model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 351 |
"model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
|
| 352 |
"model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
|
| 353 |
-
"model.layers.32.self_attn.q_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
|
| 354 |
-
"model.layers.32.self_attn.q_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
|
| 355 |
"model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
|
| 356 |
-
"model.layers.32.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
|
| 357 |
-
"model.layers.32.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
|
| 358 |
"model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
|
| 359 |
"model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 360 |
"model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
|
|
@@ -363,11 +255,7 @@
|
|
| 363 |
"model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 364 |
"model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
|
| 365 |
"model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
|
| 366 |
-
"model.layers.33.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
|
| 367 |
-
"model.layers.33.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
|
| 368 |
"model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
|
| 369 |
-
"model.layers.33.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
|
| 370 |
-
"model.layers.33.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
|
| 371 |
"model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
|
| 372 |
"model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 373 |
"model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
|
|
@@ -376,11 +264,7 @@
|
|
| 376 |
"model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 377 |
"model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
|
| 378 |
"model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
|
| 379 |
-
"model.layers.34.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
|
| 380 |
-
"model.layers.34.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
|
| 381 |
"model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
|
| 382 |
-
"model.layers.34.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
|
| 383 |
-
"model.layers.34.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
|
| 384 |
"model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
|
| 385 |
"model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 386 |
"model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
|
|
@@ -389,11 +273,7 @@
|
|
| 389 |
"model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 390 |
"model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
|
| 391 |
"model.layers.35.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
|
| 392 |
-
"model.layers.35.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
|
| 393 |
-
"model.layers.35.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
|
| 394 |
"model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
|
| 395 |
-
"model.layers.35.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
|
| 396 |
-
"model.layers.35.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
|
| 397 |
"model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
|
| 398 |
"model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 399 |
"model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
|
|
@@ -402,11 +282,7 @@
|
|
| 402 |
"model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 403 |
"model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
|
| 404 |
"model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
|
| 405 |
-
"model.layers.36.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
|
| 406 |
-
"model.layers.36.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
|
| 407 |
"model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
|
| 408 |
-
"model.layers.36.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
|
| 409 |
-
"model.layers.36.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
|
| 410 |
"model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
|
| 411 |
"model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 412 |
"model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
|
|
@@ -415,11 +291,7 @@
|
|
| 415 |
"model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 416 |
"model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
|
| 417 |
"model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
|
| 418 |
-
"model.layers.37.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
|
| 419 |
-
"model.layers.37.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
|
| 420 |
"model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
|
| 421 |
-
"model.layers.37.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
|
| 422 |
-
"model.layers.37.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
|
| 423 |
"model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
|
| 424 |
"model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 425 |
"model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
|
|
@@ -428,11 +300,7 @@
|
|
| 428 |
"model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 429 |
"model.layers.38.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
|
| 430 |
"model.layers.38.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
|
| 431 |
-
"model.layers.38.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
|
| 432 |
-
"model.layers.38.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
|
| 433 |
"model.layers.38.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
|
| 434 |
-
"model.layers.38.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
|
| 435 |
-
"model.layers.38.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
|
| 436 |
"model.layers.38.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
|
| 437 |
"model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 438 |
"model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
|
|
@@ -441,11 +309,7 @@
|
|
| 441 |
"model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 442 |
"model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
|
| 443 |
"model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
|
| 444 |
-
"model.layers.39.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
|
| 445 |
-
"model.layers.39.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
|
| 446 |
"model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
|
| 447 |
-
"model.layers.39.self_attn.v_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
|
| 448 |
-
"model.layers.39.self_attn.v_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
|
| 449 |
"model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
|
| 450 |
"model.layers.4.input_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 451 |
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
|
|
@@ -454,11 +318,7 @@
|
|
| 454 |
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 455 |
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
|
| 456 |
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
|
| 457 |
-
"model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
|
| 458 |
-
"model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
|
| 459 |
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
|
| 460 |
-
"model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
|
| 461 |
-
"model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
|
| 462 |
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
|
| 463 |
"model.layers.40.input_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 464 |
"model.layers.40.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
|
|
@@ -467,11 +327,7 @@
|
|
| 467 |
"model.layers.40.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 468 |
"model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
|
| 469 |
"model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
|
| 470 |
-
"model.layers.40.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
|
| 471 |
-
"model.layers.40.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
|
| 472 |
"model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
|
| 473 |
-
"model.layers.40.self_attn.v_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
|
| 474 |
-
"model.layers.40.self_attn.v_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
|
| 475 |
"model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
|
| 476 |
"model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
|
| 477 |
"model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
|
|
@@ -480,11 +336,7 @@
|
|
| 480 |
"model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
|
| 481 |
"model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
|
| 482 |
"model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
|
| 483 |
-
"model.layers.41.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
|
| 484 |
-
"model.layers.41.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
|
| 485 |
"model.layers.41.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
|
| 486 |
-
"model.layers.41.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
|
| 487 |
-
"model.layers.41.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
|
| 488 |
"model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
|
| 489 |
"model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
|
| 490 |
"model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
|
|
@@ -493,11 +345,7 @@
|
|
| 493 |
"model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
|
| 494 |
"model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
|
| 495 |
"model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
|
| 496 |
-
"model.layers.42.self_attn.q_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
|
| 497 |
-
"model.layers.42.self_attn.q_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
|
| 498 |
"model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
|
| 499 |
-
"model.layers.42.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
|
| 500 |
-
"model.layers.42.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
|
| 501 |
"model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
|
| 502 |
"model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 503 |
"model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
|
|
@@ -506,11 +354,7 @@
|
|
| 506 |
"model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 507 |
"model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
|
| 508 |
"model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
|
| 509 |
-
"model.layers.43.self_attn.q_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
|
| 510 |
-
"model.layers.43.self_attn.q_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
|
| 511 |
"model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
|
| 512 |
-
"model.layers.43.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
|
| 513 |
-
"model.layers.43.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
|
| 514 |
"model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
|
| 515 |
"model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 516 |
"model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
|
|
@@ -519,11 +363,7 @@
|
|
| 519 |
"model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 520 |
"model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
|
| 521 |
"model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
|
| 522 |
-
"model.layers.44.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
|
| 523 |
-
"model.layers.44.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
|
| 524 |
"model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
|
| 525 |
-
"model.layers.44.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
|
| 526 |
-
"model.layers.44.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
|
| 527 |
"model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
|
| 528 |
"model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 529 |
"model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
|
|
@@ -532,11 +372,7 @@
|
|
| 532 |
"model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 533 |
"model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
|
| 534 |
"model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
|
| 535 |
-
"model.layers.45.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
|
| 536 |
-
"model.layers.45.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
|
| 537 |
"model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
|
| 538 |
-
"model.layers.45.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
|
| 539 |
-
"model.layers.45.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
|
| 540 |
"model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
|
| 541 |
"model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 542 |
"model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
|
|
@@ -545,11 +381,7 @@
|
|
| 545 |
"model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 546 |
"model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
|
| 547 |
"model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
|
| 548 |
-
"model.layers.46.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
|
| 549 |
-
"model.layers.46.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
|
| 550 |
"model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
|
| 551 |
-
"model.layers.46.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
|
| 552 |
-
"model.layers.46.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
|
| 553 |
"model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
|
| 554 |
"model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 555 |
"model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
|
|
@@ -558,11 +390,7 @@
|
|
| 558 |
"model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 559 |
"model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
|
| 560 |
"model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
|
| 561 |
-
"model.layers.47.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
|
| 562 |
-
"model.layers.47.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
|
| 563 |
"model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
|
| 564 |
-
"model.layers.47.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
|
| 565 |
-
"model.layers.47.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
|
| 566 |
"model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
|
| 567 |
"model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 568 |
"model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
|
|
@@ -571,11 +399,7 @@
|
|
| 571 |
"model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 572 |
"model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
|
| 573 |
"model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
|
| 574 |
-
"model.layers.48.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
|
| 575 |
-
"model.layers.48.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
|
| 576 |
"model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
|
| 577 |
-
"model.layers.48.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
|
| 578 |
-
"model.layers.48.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
|
| 579 |
"model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
|
| 580 |
"model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 581 |
"model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
|
|
@@ -584,11 +408,7 @@
|
|
| 584 |
"model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 585 |
"model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
|
| 586 |
"model.layers.49.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
|
| 587 |
-
"model.layers.49.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
|
| 588 |
-
"model.layers.49.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
|
| 589 |
"model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
|
| 590 |
-
"model.layers.49.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
|
| 591 |
-
"model.layers.49.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
|
| 592 |
"model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
|
| 593 |
"model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 594 |
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
|
|
@@ -597,11 +417,7 @@
|
|
| 597 |
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 598 |
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
|
| 599 |
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
|
| 600 |
-
"model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
|
| 601 |
-
"model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
|
| 602 |
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
|
| 603 |
-
"model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
|
| 604 |
-
"model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
|
| 605 |
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
|
| 606 |
"model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 607 |
"model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
|
|
@@ -610,11 +426,7 @@
|
|
| 610 |
"model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 611 |
"model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
|
| 612 |
"model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
|
| 613 |
-
"model.layers.50.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
|
| 614 |
-
"model.layers.50.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
|
| 615 |
"model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
|
| 616 |
-
"model.layers.50.self_attn.v_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
|
| 617 |
-
"model.layers.50.self_attn.v_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
|
| 618 |
"model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
|
| 619 |
"model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 620 |
"model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
|
|
@@ -623,11 +435,7 @@
|
|
| 623 |
"model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 624 |
"model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
|
| 625 |
"model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
|
| 626 |
-
"model.layers.51.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
|
| 627 |
-
"model.layers.51.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
|
| 628 |
"model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
|
| 629 |
-
"model.layers.51.self_attn.v_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
|
| 630 |
-
"model.layers.51.self_attn.v_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
|
| 631 |
"model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
|
| 632 |
"model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
|
| 633 |
"model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
|
|
@@ -636,11 +444,7 @@
|
|
| 636 |
"model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
|
| 637 |
"model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
|
| 638 |
"model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
|
| 639 |
-
"model.layers.52.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
|
| 640 |
-
"model.layers.52.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
|
| 641 |
"model.layers.52.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
|
| 642 |
-
"model.layers.52.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
|
| 643 |
-
"model.layers.52.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
|
| 644 |
"model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
|
| 645 |
"model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
|
| 646 |
"model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
|
|
@@ -649,11 +453,7 @@
|
|
| 649 |
"model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
|
| 650 |
"model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
|
| 651 |
"model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
|
| 652 |
-
"model.layers.53.self_attn.q_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
|
| 653 |
-
"model.layers.53.self_attn.q_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
|
| 654 |
"model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
|
| 655 |
-
"model.layers.53.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
|
| 656 |
-
"model.layers.53.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
|
| 657 |
"model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
|
| 658 |
"model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 659 |
"model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
|
|
@@ -662,11 +462,7 @@
|
|
| 662 |
"model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 663 |
"model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
|
| 664 |
"model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
|
| 665 |
-
"model.layers.54.self_attn.q_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
|
| 666 |
-
"model.layers.54.self_attn.q_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
|
| 667 |
"model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
|
| 668 |
-
"model.layers.54.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
|
| 669 |
-
"model.layers.54.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
|
| 670 |
"model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
|
| 671 |
"model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 672 |
"model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
|
|
@@ -675,11 +471,7 @@
|
|
| 675 |
"model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 676 |
"model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
|
| 677 |
"model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
|
| 678 |
-
"model.layers.55.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
|
| 679 |
-
"model.layers.55.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
|
| 680 |
"model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
|
| 681 |
-
"model.layers.55.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
|
| 682 |
-
"model.layers.55.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
|
| 683 |
"model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
|
| 684 |
"model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 685 |
"model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
|
|
@@ -688,11 +480,7 @@
|
|
| 688 |
"model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 689 |
"model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
|
| 690 |
"model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
|
| 691 |
-
"model.layers.56.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
|
| 692 |
-
"model.layers.56.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
|
| 693 |
"model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
|
| 694 |
-
"model.layers.56.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
|
| 695 |
-
"model.layers.56.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
|
| 696 |
"model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
|
| 697 |
"model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 698 |
"model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
|
|
@@ -701,11 +489,7 @@
|
|
| 701 |
"model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 702 |
"model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
|
| 703 |
"model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
|
| 704 |
-
"model.layers.57.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
|
| 705 |
-
"model.layers.57.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
|
| 706 |
"model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
|
| 707 |
-
"model.layers.57.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
|
| 708 |
-
"model.layers.57.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
|
| 709 |
"model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
|
| 710 |
"model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 711 |
"model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
|
|
@@ -714,11 +498,7 @@
|
|
| 714 |
"model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 715 |
"model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
|
| 716 |
"model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
|
| 717 |
-
"model.layers.58.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
|
| 718 |
-
"model.layers.58.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
|
| 719 |
"model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
|
| 720 |
-
"model.layers.58.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
|
| 721 |
-
"model.layers.58.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
|
| 722 |
"model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
|
| 723 |
"model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 724 |
"model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
|
|
@@ -727,11 +507,7 @@
|
|
| 727 |
"model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 728 |
"model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
|
| 729 |
"model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
|
| 730 |
-
"model.layers.59.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
|
| 731 |
-
"model.layers.59.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
|
| 732 |
"model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
|
| 733 |
-
"model.layers.59.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
|
| 734 |
-
"model.layers.59.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
|
| 735 |
"model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
|
| 736 |
"model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 737 |
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
|
|
@@ -740,11 +516,7 @@
|
|
| 740 |
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 741 |
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
|
| 742 |
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
|
| 743 |
-
"model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
|
| 744 |
-
"model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
|
| 745 |
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
|
| 746 |
-
"model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
|
| 747 |
-
"model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
|
| 748 |
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
|
| 749 |
"model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 750 |
"model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
|
|
@@ -753,11 +525,7 @@
|
|
| 753 |
"model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 754 |
"model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
|
| 755 |
"model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
|
| 756 |
-
"model.layers.60.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
|
| 757 |
-
"model.layers.60.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
|
| 758 |
"model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
|
| 759 |
-
"model.layers.60.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
|
| 760 |
-
"model.layers.60.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
|
| 761 |
"model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
|
| 762 |
"model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 763 |
"model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
|
|
@@ -766,11 +534,7 @@
|
|
| 766 |
"model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 767 |
"model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
|
| 768 |
"model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
|
| 769 |
-
"model.layers.61.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
|
| 770 |
-
"model.layers.61.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
|
| 771 |
"model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
|
| 772 |
-
"model.layers.61.self_attn.v_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
|
| 773 |
-
"model.layers.61.self_attn.v_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
|
| 774 |
"model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
|
| 775 |
"model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 776 |
"model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
|
|
@@ -779,11 +543,7 @@
|
|
| 779 |
"model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 780 |
"model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
|
| 781 |
"model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
|
| 782 |
-
"model.layers.62.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
|
| 783 |
-
"model.layers.62.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
|
| 784 |
"model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
|
| 785 |
-
"model.layers.62.self_attn.v_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
|
| 786 |
-
"model.layers.62.self_attn.v_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
|
| 787 |
"model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
|
| 788 |
"model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
|
| 789 |
"model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
|
|
@@ -792,11 +552,7 @@
|
|
| 792 |
"model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
|
| 793 |
"model.layers.63.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
|
| 794 |
"model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
|
| 795 |
-
"model.layers.63.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
|
| 796 |
-
"model.layers.63.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
|
| 797 |
"model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
|
| 798 |
-
"model.layers.63.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
|
| 799 |
-
"model.layers.63.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
|
| 800 |
"model.layers.63.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
|
| 801 |
"model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
|
| 802 |
"model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
|
|
@@ -805,11 +561,7 @@
|
|
| 805 |
"model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
|
| 806 |
"model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
|
| 807 |
"model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
|
| 808 |
-
"model.layers.64.self_attn.q_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
|
| 809 |
-
"model.layers.64.self_attn.q_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
|
| 810 |
"model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
|
| 811 |
-
"model.layers.64.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
|
| 812 |
-
"model.layers.64.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
|
| 813 |
"model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
|
| 814 |
"model.layers.65.input_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 815 |
"model.layers.65.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
|
|
@@ -818,11 +570,7 @@
|
|
| 818 |
"model.layers.65.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 819 |
"model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
|
| 820 |
"model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
|
| 821 |
-
"model.layers.65.self_attn.q_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
|
| 822 |
-
"model.layers.65.self_attn.q_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
|
| 823 |
"model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
|
| 824 |
-
"model.layers.65.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
|
| 825 |
-
"model.layers.65.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
|
| 826 |
"model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
|
| 827 |
"model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 828 |
"model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
|
|
@@ -831,11 +579,7 @@
|
|
| 831 |
"model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 832 |
"model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
|
| 833 |
"model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
|
| 834 |
-
"model.layers.66.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
|
| 835 |
-
"model.layers.66.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
|
| 836 |
"model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
|
| 837 |
-
"model.layers.66.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
|
| 838 |
-
"model.layers.66.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
|
| 839 |
"model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
|
| 840 |
"model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 841 |
"model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
|
|
@@ -844,11 +588,7 @@
|
|
| 844 |
"model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 845 |
"model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
|
| 846 |
"model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
|
| 847 |
-
"model.layers.67.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
|
| 848 |
-
"model.layers.67.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
|
| 849 |
"model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
|
| 850 |
-
"model.layers.67.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
|
| 851 |
-
"model.layers.67.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
|
| 852 |
"model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
|
| 853 |
"model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 854 |
"model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
|
|
@@ -857,11 +597,7 @@
|
|
| 857 |
"model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 858 |
"model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
|
| 859 |
"model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
|
| 860 |
-
"model.layers.68.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
|
| 861 |
-
"model.layers.68.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
|
| 862 |
"model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
|
| 863 |
-
"model.layers.68.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
|
| 864 |
-
"model.layers.68.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
|
| 865 |
"model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
|
| 866 |
"model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 867 |
"model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
|
|
@@ -870,11 +606,7 @@
|
|
| 870 |
"model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 871 |
"model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
|
| 872 |
"model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
|
| 873 |
-
"model.layers.69.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
|
| 874 |
-
"model.layers.69.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
|
| 875 |
"model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
|
| 876 |
-
"model.layers.69.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
|
| 877 |
-
"model.layers.69.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
|
| 878 |
"model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
|
| 879 |
"model.layers.7.input_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 880 |
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
|
|
@@ -883,11 +615,7 @@
|
|
| 883 |
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 884 |
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
|
| 885 |
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
|
| 886 |
-
"model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
|
| 887 |
-
"model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
|
| 888 |
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
|
| 889 |
-
"model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
|
| 890 |
-
"model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
|
| 891 |
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
|
| 892 |
"model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 893 |
"model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
|
|
@@ -896,11 +624,7 @@
|
|
| 896 |
"model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 897 |
"model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
|
| 898 |
"model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
|
| 899 |
-
"model.layers.70.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
|
| 900 |
-
"model.layers.70.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
|
| 901 |
"model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
|
| 902 |
-
"model.layers.70.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
|
| 903 |
-
"model.layers.70.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
|
| 904 |
"model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
|
| 905 |
"model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 906 |
"model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
|
|
@@ -909,11 +633,7 @@
|
|
| 909 |
"model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 910 |
"model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
|
| 911 |
"model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
|
| 912 |
-
"model.layers.71.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
|
| 913 |
-
"model.layers.71.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
|
| 914 |
"model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
|
| 915 |
-
"model.layers.71.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
|
| 916 |
-
"model.layers.71.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
|
| 917 |
"model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
|
| 918 |
"model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 919 |
"model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
|
|
@@ -922,11 +642,7 @@
|
|
| 922 |
"model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 923 |
"model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
|
| 924 |
"model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
|
| 925 |
-
"model.layers.72.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
|
| 926 |
-
"model.layers.72.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
|
| 927 |
"model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
|
| 928 |
-
"model.layers.72.self_attn.v_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
|
| 929 |
-
"model.layers.72.self_attn.v_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
|
| 930 |
"model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
|
| 931 |
"model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 932 |
"model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
|
|
@@ -935,11 +651,7 @@
|
|
| 935 |
"model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 936 |
"model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
|
| 937 |
"model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
|
| 938 |
-
"model.layers.73.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
|
| 939 |
-
"model.layers.73.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
|
| 940 |
"model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
|
| 941 |
-
"model.layers.73.self_attn.v_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
|
| 942 |
-
"model.layers.73.self_attn.v_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
|
| 943 |
"model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
|
| 944 |
"model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
|
| 945 |
"model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
|
|
@@ -948,11 +660,7 @@
|
|
| 948 |
"model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
|
| 949 |
"model.layers.74.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
|
| 950 |
"model.layers.74.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
|
| 951 |
-
"model.layers.74.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
|
| 952 |
-
"model.layers.74.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
|
| 953 |
"model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
|
| 954 |
-
"model.layers.74.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
|
| 955 |
-
"model.layers.74.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
|
| 956 |
"model.layers.74.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
|
| 957 |
"model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
|
| 958 |
"model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
|
|
@@ -961,11 +669,7 @@
|
|
| 961 |
"model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
|
| 962 |
"model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
|
| 963 |
"model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
|
| 964 |
-
"model.layers.75.self_attn.q_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
|
| 965 |
-
"model.layers.75.self_attn.q_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
|
| 966 |
"model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
|
| 967 |
-
"model.layers.75.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
|
| 968 |
-
"model.layers.75.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
|
| 969 |
"model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
|
| 970 |
"model.layers.76.input_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 971 |
"model.layers.76.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
|
|
@@ -974,11 +678,7 @@
|
|
| 974 |
"model.layers.76.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 975 |
"model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
|
| 976 |
"model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
|
| 977 |
-
"model.layers.76.self_attn.q_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
|
| 978 |
-
"model.layers.76.self_attn.q_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
|
| 979 |
"model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
|
| 980 |
-
"model.layers.76.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
|
| 981 |
-
"model.layers.76.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
|
| 982 |
"model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
|
| 983 |
"model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 984 |
"model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
|
|
@@ -987,11 +687,7 @@
|
|
| 987 |
"model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 988 |
"model.layers.77.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
|
| 989 |
"model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
|
| 990 |
-
"model.layers.77.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
|
| 991 |
-
"model.layers.77.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
|
| 992 |
"model.layers.77.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
|
| 993 |
-
"model.layers.77.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
|
| 994 |
-
"model.layers.77.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
|
| 995 |
"model.layers.77.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
|
| 996 |
"model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 997 |
"model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
|
|
@@ -1000,11 +696,7 @@
|
|
| 1000 |
"model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 1001 |
"model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
|
| 1002 |
"model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
|
| 1003 |
-
"model.layers.78.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
|
| 1004 |
-
"model.layers.78.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
|
| 1005 |
"model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
|
| 1006 |
-
"model.layers.78.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
|
| 1007 |
-
"model.layers.78.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
|
| 1008 |
"model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
|
| 1009 |
"model.layers.79.input_layernorm.weight": "model-00030-of-00030.safetensors",
|
| 1010 |
"model.layers.79.mlp.down_proj.weight": "model-00030-of-00030.safetensors",
|
|
@@ -1013,11 +705,7 @@
|
|
| 1013 |
"model.layers.79.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
|
| 1014 |
"model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
|
| 1015 |
"model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
|
| 1016 |
-
"model.layers.79.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
|
| 1017 |
-
"model.layers.79.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
|
| 1018 |
"model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
|
| 1019 |
-
"model.layers.79.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
|
| 1020 |
-
"model.layers.79.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
|
| 1021 |
"model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
|
| 1022 |
"model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
|
| 1023 |
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
|
|
@@ -1026,11 +714,7 @@
|
|
| 1026 |
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
|
| 1027 |
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
|
| 1028 |
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
|
| 1029 |
-
"model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
|
| 1030 |
-
"model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
|
| 1031 |
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
|
| 1032 |
-
"model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
|
| 1033 |
-
"model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
|
| 1034 |
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
|
| 1035 |
"model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
|
| 1036 |
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
|
|
@@ -1039,12 +723,8 @@
|
|
| 1039 |
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
|
| 1040 |
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
|
| 1041 |
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
|
| 1042 |
-
"model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
|
| 1043 |
-
"model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
|
| 1044 |
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
|
| 1045 |
-
"model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
|
| 1046 |
-
"model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
|
| 1047 |
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
|
| 1048 |
"model.norm.weight": "model-00030-of-00030.safetensors"
|
| 1049 |
}
|
| 1050 |
-
}
|
|
|
|
| 12 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
|
| 13 |
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
|
| 14 |
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
|
|
|
|
|
|
|
| 15 |
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
|
|
|
|
|
|
|
| 16 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
|
| 17 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00030.safetensors",
|
| 18 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
|
|
|
|
| 21 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
|
| 22 |
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
|
| 23 |
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
|
|
|
|
|
|
|
| 24 |
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
|
|
|
|
|
|
|
| 25 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
|
| 26 |
"model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 27 |
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
| 30 |
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 31 |
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
|
| 32 |
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
|
|
|
|
|
|
|
| 33 |
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
|
|
|
|
|
|
|
| 34 |
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
|
| 35 |
"model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 36 |
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
| 39 |
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 40 |
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
|
| 41 |
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
|
|
|
| 42 |
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
|
|
|
| 43 |
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
|
| 44 |
"model.layers.12.input_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 45 |
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
| 48 |
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
|
| 49 |
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
|
| 50 |
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
|
|
|
| 51 |
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
|
|
|
| 52 |
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
|
| 53 |
"model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 54 |
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
| 57 |
"model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 58 |
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
|
| 59 |
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
|
|
|
| 60 |
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
|
|
|
|
|
|
|
| 61 |
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
|
| 62 |
"model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 63 |
"model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
| 66 |
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 67 |
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
|
| 68 |
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
|
|
|
| 69 |
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
|
|
|
| 70 |
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
|
| 71 |
"model.layers.15.input_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 72 |
"model.layers.15.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
| 75 |
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
|
| 76 |
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
|
| 77 |
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
|
|
|
| 78 |
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
|
|
|
| 79 |
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
|
| 80 |
"model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 81 |
"model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
|
|
|
|
| 84 |
"model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 85 |
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
|
| 86 |
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
|
|
|
| 87 |
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
|
|
|
|
|
|
|
| 88 |
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
|
| 89 |
"model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 90 |
"model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
|
|
|
|
| 93 |
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 94 |
"model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
|
| 95 |
"model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
|
|
|
|
|
|
|
| 96 |
"model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
|
|
|
|
|
|
|
| 97 |
"model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
|
| 98 |
"model.layers.18.input_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 99 |
"model.layers.18.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
|
|
|
|
| 102 |
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
|
| 103 |
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
|
| 104 |
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
|
|
|
|
|
|
|
| 105 |
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
|
|
|
|
|
|
|
| 106 |
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
|
| 107 |
"model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
|
| 108 |
"model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
|
|
|
|
| 111 |
"model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
|
| 112 |
"model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
|
| 113 |
"model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
|
|
|
|
|
|
|
| 114 |
"model.layers.19.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
|
|
|
|
|
|
|
| 115 |
"model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
|
| 116 |
"model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 117 |
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
| 120 |
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 121 |
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
|
| 122 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
|
|
|
|
|
|
|
| 123 |
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
|
|
|
|
|
|
|
| 124 |
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
|
| 125 |
"model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
|
| 126 |
"model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
|
|
|
|
| 129 |
"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
|
| 130 |
"model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
|
| 131 |
"model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
|
|
|
|
|
|
|
| 132 |
"model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
|
|
|
|
|
|
|
| 133 |
"model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
|
| 134 |
"model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 135 |
"model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
| 138 |
"model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 139 |
"model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
|
| 140 |
"model.layers.21.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
|
|
|
|
|
|
|
| 141 |
"model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
|
|
|
|
|
|
|
| 142 |
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
|
| 143 |
"model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 144 |
"model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
| 147 |
"model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 148 |
"model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
|
| 149 |
"model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
|
|
|
| 150 |
"model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
|
|
|
| 151 |
"model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
|
| 152 |
"model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 153 |
"model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
| 156 |
"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
|
| 157 |
"model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
|
| 158 |
"model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
|
|
|
| 159 |
"model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
|
|
|
| 160 |
"model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
|
| 161 |
"model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 162 |
"model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
| 165 |
"model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 166 |
"model.layers.24.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
|
| 167 |
"model.layers.24.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
|
|
|
| 168 |
"model.layers.24.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
|
|
|
|
|
|
|
| 169 |
"model.layers.24.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
|
| 170 |
"model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 171 |
"model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
| 174 |
"model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 175 |
"model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
|
| 176 |
"model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
|
|
|
| 177 |
"model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
|
|
|
| 178 |
"model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
|
| 179 |
"model.layers.26.input_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 180 |
"model.layers.26.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
| 183 |
"model.layers.26.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
|
| 184 |
"model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
|
| 185 |
"model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
|
|
|
| 186 |
"model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
|
|
|
| 187 |
"model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
|
| 188 |
"model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 189 |
"model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
|
|
|
|
| 192 |
"model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 193 |
"model.layers.27.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
|
| 194 |
"model.layers.27.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
|
|
|
| 195 |
"model.layers.27.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
|
|
|
|
|
|
|
| 196 |
"model.layers.27.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
|
| 197 |
"model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 198 |
"model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
|
|
|
|
| 201 |
"model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 202 |
"model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
|
| 203 |
"model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
|
|
|
|
|
|
|
| 204 |
"model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
|
|
|
|
|
|
|
| 205 |
"model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
|
| 206 |
"model.layers.29.input_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 207 |
"model.layers.29.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
|
|
|
|
| 210 |
"model.layers.29.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
|
| 211 |
"model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
|
| 212 |
"model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
|
|
|
|
|
|
|
| 213 |
"model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
|
|
|
|
|
|
|
| 214 |
"model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
|
| 215 |
"model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 216 |
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
| 219 |
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 220 |
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
|
| 221 |
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
|
|
|
| 222 |
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
|
|
|
| 223 |
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
|
| 224 |
"model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
|
| 225 |
"model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
|
|
|
|
| 228 |
"model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
|
| 229 |
"model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
|
| 230 |
"model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
|
|
|
|
|
|
|
| 231 |
"model.layers.30.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
|
|
|
|
|
|
|
| 232 |
"model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
|
| 233 |
"model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
|
| 234 |
"model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
|
|
|
|
| 237 |
"model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
|
| 238 |
"model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
|
| 239 |
"model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
|
|
|
|
|
|
|
| 240 |
"model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
|
|
|
|
|
|
|
| 241 |
"model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
|
| 242 |
"model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 243 |
"model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
| 246 |
"model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 247 |
"model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
|
| 248 |
"model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
|
|
|
|
|
|
|
| 249 |
"model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
|
|
|
|
|
|
|
| 250 |
"model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
|
| 251 |
"model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 252 |
"model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
| 255 |
"model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 256 |
"model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
|
| 257 |
"model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
|
|
|
| 258 |
"model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
|
|
|
| 259 |
"model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
|
| 260 |
"model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 261 |
"model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
| 264 |
"model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
|
| 265 |
"model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
|
| 266 |
"model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
|
|
|
| 267 |
"model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
|
|
|
| 268 |
"model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
|
| 269 |
"model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 270 |
"model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
| 273 |
"model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 274 |
"model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
|
| 275 |
"model.layers.35.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
|
|
|
| 276 |
"model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
|
|
|
|
|
|
|
| 277 |
"model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
|
| 278 |
"model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 279 |
"model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
| 282 |
"model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 283 |
"model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
|
| 284 |
"model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
|
|
|
| 285 |
"model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
|
|
|
| 286 |
"model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
|
| 287 |
"model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 288 |
"model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
| 291 |
"model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
|
| 292 |
"model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
|
| 293 |
"model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
|
|
|
| 294 |
"model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
|
|
|
| 295 |
"model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
|
| 296 |
"model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 297 |
"model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
|
|
|
|
| 300 |
"model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 301 |
"model.layers.38.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
|
| 302 |
"model.layers.38.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
|
|
|
| 303 |
"model.layers.38.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
|
|
|
|
|
|
|
| 304 |
"model.layers.38.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
|
| 305 |
"model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 306 |
"model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
|
|
|
|
| 309 |
"model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 310 |
"model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
|
| 311 |
"model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
|
|
|
|
|
|
|
| 312 |
"model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
|
|
|
|
|
|
|
| 313 |
"model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
|
| 314 |
"model.layers.4.input_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 315 |
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
| 318 |
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
|
| 319 |
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
|
| 320 |
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
|
|
|
| 321 |
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
|
|
|
| 322 |
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
|
| 323 |
"model.layers.40.input_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 324 |
"model.layers.40.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
|
|
|
|
| 327 |
"model.layers.40.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
|
| 328 |
"model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
|
| 329 |
"model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
|
|
|
|
|
|
|
| 330 |
"model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
|
|
|
|
|
|
|
| 331 |
"model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
|
| 332 |
"model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
|
| 333 |
"model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
|
|
|
|
| 336 |
"model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
|
| 337 |
"model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
|
| 338 |
"model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
|
|
|
|
|
|
|
| 339 |
"model.layers.41.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
|
|
|
|
|
|
|
| 340 |
"model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
|
| 341 |
"model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
|
| 342 |
"model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
|
|
|
|
| 345 |
"model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
|
| 346 |
"model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
|
| 347 |
"model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
|
|
|
|
|
|
|
| 348 |
"model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
|
|
|
|
|
|
|
| 349 |
"model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
|
| 350 |
"model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 351 |
"model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
| 354 |
"model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 355 |
"model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
|
| 356 |
"model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
|
|
|
|
|
|
|
| 357 |
"model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
|
|
|
|
|
|
|
| 358 |
"model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
|
| 359 |
"model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 360 |
"model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
| 363 |
"model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 364 |
"model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
|
| 365 |
"model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
|
|
|
| 366 |
"model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
|
|
|
| 367 |
"model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
|
| 368 |
"model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 369 |
"model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
| 372 |
"model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
|
| 373 |
"model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
|
| 374 |
"model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
|
|
|
| 375 |
"model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
|
|
|
| 376 |
"model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
|
| 377 |
"model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 378 |
"model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
| 381 |
"model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 382 |
"model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
|
| 383 |
"model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
|
|
|
| 384 |
"model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
|
|
|
|
|
|
|
| 385 |
"model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
|
| 386 |
"model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 387 |
"model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
| 390 |
"model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 391 |
"model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
|
| 392 |
"model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
|
|
|
| 393 |
"model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
|
|
|
| 394 |
"model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
|
| 395 |
"model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 396 |
"model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
| 399 |
"model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
|
| 400 |
"model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
|
| 401 |
"model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
|
|
|
| 402 |
"model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
|
|
|
| 403 |
"model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
|
| 404 |
"model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 405 |
"model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
|
|
|
|
| 408 |
"model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 409 |
"model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
|
| 410 |
"model.layers.49.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
|
|
|
| 411 |
"model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
|
|
|
|
|
|
|
| 412 |
"model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
|
| 413 |
"model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 414 |
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
|
|
|
|
| 417 |
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 418 |
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
|
| 419 |
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
|
|
|
| 420 |
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
|
|
|
|
|
|
|
| 421 |
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
|
| 422 |
"model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 423 |
"model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
|
|
|
|
| 426 |
"model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 427 |
"model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
|
| 428 |
"model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
|
|
|
|
|
|
|
| 429 |
"model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
|
|
|
|
|
|
|
| 430 |
"model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
|
| 431 |
"model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 432 |
"model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
|
|
|
|
| 435 |
"model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
|
| 436 |
"model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
|
| 437 |
"model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
|
|
|
|
|
|
|
| 438 |
"model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
|
|
|
|
|
|
|
| 439 |
"model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
|
| 440 |
"model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
|
| 441 |
"model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
|
|
|
|
| 444 |
"model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
|
| 445 |
"model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
|
| 446 |
"model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
|
|
|
|
|
|
|
| 447 |
"model.layers.52.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
|
|
|
|
|
|
|
| 448 |
"model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
|
| 449 |
"model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
|
| 450 |
"model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
|
|
|
|
| 453 |
"model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
|
| 454 |
"model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
|
| 455 |
"model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
|
|
|
|
|
|
|
| 456 |
"model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
|
|
|
|
|
|
|
| 457 |
"model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
|
| 458 |
"model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 459 |
"model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
| 462 |
"model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 463 |
"model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
|
| 464 |
"model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
|
|
|
|
|
|
|
| 465 |
"model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
|
|
|
|
|
|
|
| 466 |
"model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
|
| 467 |
"model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 468 |
"model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
| 471 |
"model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 472 |
"model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
|
| 473 |
"model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
|
|
|
| 474 |
"model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
|
|
|
| 475 |
"model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
|
| 476 |
"model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 477 |
"model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
| 480 |
"model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
|
| 481 |
"model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
|
| 482 |
"model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
|
|
|
| 483 |
"model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
|
|
|
| 484 |
"model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
|
| 485 |
"model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 486 |
"model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
| 489 |
"model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 490 |
"model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
|
| 491 |
"model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
|
|
|
| 492 |
"model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
|
|
|
|
|
|
|
| 493 |
"model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
|
| 494 |
"model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 495 |
"model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
| 498 |
"model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 499 |
"model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
|
| 500 |
"model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
|
|
|
| 501 |
"model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
|
|
|
| 502 |
"model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
|
| 503 |
"model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 504 |
"model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
| 507 |
"model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
|
| 508 |
"model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
|
| 509 |
"model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
|
|
|
| 510 |
"model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
|
|
|
| 511 |
"model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
|
| 512 |
"model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 513 |
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
|
|
|
|
| 516 |
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 517 |
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
|
| 518 |
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
|
|
|
|
|
|
|
| 519 |
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
|
|
|
|
|
|
|
| 520 |
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
|
| 521 |
"model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 522 |
"model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
|
|
|
|
| 525 |
"model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 526 |
"model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
|
| 527 |
"model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
|
|
|
| 528 |
"model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
|
|
|
|
|
|
|
| 529 |
"model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
|
| 530 |
"model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 531 |
"model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
|
|
|
|
| 534 |
"model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 535 |
"model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
|
| 536 |
"model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
|
|
|
|
|
|
|
| 537 |
"model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
|
|
|
|
|
|
|
| 538 |
"model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
|
| 539 |
"model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 540 |
"model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
|
|
|
|
| 543 |
"model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
|
| 544 |
"model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
|
| 545 |
"model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
|
|
|
|
|
|
|
| 546 |
"model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
|
|
|
|
|
|
|
| 547 |
"model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
|
| 548 |
"model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
|
| 549 |
"model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
|
|
|
|
| 552 |
"model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
|
| 553 |
"model.layers.63.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
|
| 554 |
"model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
|
|
|
|
|
|
|
| 555 |
"model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
|
|
|
|
|
|
|
| 556 |
"model.layers.63.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
|
| 557 |
"model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
|
| 558 |
"model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
|
|
|
|
| 561 |
"model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
|
| 562 |
"model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
|
| 563 |
"model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
|
|
|
|
|
|
|
| 564 |
"model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
|
|
|
|
|
|
|
| 565 |
"model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
|
| 566 |
"model.layers.65.input_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 567 |
"model.layers.65.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
| 570 |
"model.layers.65.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 571 |
"model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
|
| 572 |
"model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
|
|
|
|
|
|
|
| 573 |
"model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
|
|
|
|
|
|
|
| 574 |
"model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
|
| 575 |
"model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 576 |
"model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
| 579 |
"model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 580 |
"model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
|
| 581 |
"model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
|
|
|
| 582 |
"model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
|
|
|
| 583 |
"model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
|
| 584 |
"model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 585 |
"model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
| 588 |
"model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
|
| 589 |
"model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
|
| 590 |
"model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
|
|
|
| 591 |
"model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
|
|
|
| 592 |
"model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
|
| 593 |
"model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 594 |
"model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
| 597 |
"model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 598 |
"model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
|
| 599 |
"model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
|
|
|
| 600 |
"model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
|
|
|
|
|
|
|
| 601 |
"model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
|
| 602 |
"model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 603 |
"model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
| 606 |
"model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 607 |
"model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
|
| 608 |
"model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
|
|
|
| 609 |
"model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
|
|
|
| 610 |
"model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
|
| 611 |
"model.layers.7.input_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 612 |
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
|
|
|
|
| 615 |
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
|
| 616 |
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
|
| 617 |
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
|
|
|
|
|
|
|
| 618 |
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
|
|
|
|
|
|
|
| 619 |
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
|
| 620 |
"model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 621 |
"model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
| 624 |
"model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
|
| 625 |
"model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
|
| 626 |
"model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
|
|
|
| 627 |
"model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
|
|
|
| 628 |
"model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
|
| 629 |
"model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 630 |
"model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
|
|
|
|
| 633 |
"model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 634 |
"model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
|
| 635 |
"model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
|
|
|
| 636 |
"model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
|
|
|
|
|
|
|
| 637 |
"model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
|
| 638 |
"model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 639 |
"model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
|
|
|
|
| 642 |
"model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 643 |
"model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
|
| 644 |
"model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
|
|
|
|
|
|
|
| 645 |
"model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
|
|
|
|
|
|
|
| 646 |
"model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
|
| 647 |
"model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 648 |
"model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
|
|
|
|
| 651 |
"model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
|
| 652 |
"model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
|
| 653 |
"model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
|
|
|
|
|
|
|
| 654 |
"model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
|
|
|
|
|
|
|
| 655 |
"model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
|
| 656 |
"model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
|
| 657 |
"model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
|
|
|
|
| 660 |
"model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
|
| 661 |
"model.layers.74.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
|
| 662 |
"model.layers.74.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
|
|
|
|
|
|
|
| 663 |
"model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
|
|
|
|
|
|
|
| 664 |
"model.layers.74.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
|
| 665 |
"model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
|
| 666 |
"model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
|
|
|
|
| 669 |
"model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
|
| 670 |
"model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
|
| 671 |
"model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
|
|
|
|
|
|
|
| 672 |
"model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
|
|
|
|
|
|
|
| 673 |
"model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
|
| 674 |
"model.layers.76.input_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 675 |
"model.layers.76.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
| 678 |
"model.layers.76.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 679 |
"model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
|
| 680 |
"model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
|
|
|
|
|
|
|
| 681 |
"model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
|
|
|
|
|
|
|
| 682 |
"model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
|
| 683 |
"model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 684 |
"model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
| 687 |
"model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 688 |
"model.layers.77.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
|
| 689 |
"model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
|
|
|
| 690 |
"model.layers.77.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
|
|
|
| 691 |
"model.layers.77.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
|
| 692 |
"model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 693 |
"model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
| 696 |
"model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
|
| 697 |
"model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
|
| 698 |
"model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
|
|
|
| 699 |
"model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
|
|
|
| 700 |
"model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
|
| 701 |
"model.layers.79.input_layernorm.weight": "model-00030-of-00030.safetensors",
|
| 702 |
"model.layers.79.mlp.down_proj.weight": "model-00030-of-00030.safetensors",
|
|
|
|
| 705 |
"model.layers.79.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
|
| 706 |
"model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
|
| 707 |
"model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
|
|
|
| 708 |
"model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
|
|
|
|
|
|
|
| 709 |
"model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
|
| 710 |
"model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
|
| 711 |
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
|
|
|
|
| 714 |
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
|
| 715 |
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
|
| 716 |
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
|
|
|
|
|
|
|
| 717 |
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
|
|
|
|
|
|
|
| 718 |
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
|
| 719 |
"model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
|
| 720 |
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
|
|
|
|
| 723 |
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
|
| 724 |
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
|
| 725 |
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
|
|
|
|
|
|
|
| 726 |
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
|
|
|
|
|
|
|
| 727 |
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
|
| 728 |
"model.norm.weight": "model-00030-of-00030.safetensors"
|
| 729 |
}
|
| 730 |
+
}
|
tokenizer.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 8192,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
tokenizer_config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
"eos_token": "</s>",
|
| 32 |
"legacy": false,
|
| 33 |
-
"max_length":
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
"pad_token": "</s>",
|
| 36 |
"padding_side": "right",
|
|
|
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
"eos_token": "</s>",
|
| 32 |
"legacy": false,
|
| 33 |
+
"max_length": 8192,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
"pad_token": "</s>",
|
| 36 |
"padding_side": "right",
|