hafidhsoekma
commited on
Commit
•
becc062
1
Parent(s):
22895cd
Upload LlamaForCausalLM
Browse files- config.json +27 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00028.bin +3 -0
- pytorch_model-00002-of-00028.bin +3 -0
- pytorch_model-00003-of-00028.bin +3 -0
- pytorch_model-00004-of-00028.bin +3 -0
- pytorch_model-00005-of-00028.bin +3 -0
- pytorch_model-00006-of-00028.bin +3 -0
- pytorch_model-00007-of-00028.bin +3 -0
- pytorch_model-00008-of-00028.bin +3 -0
- pytorch_model-00009-of-00028.bin +3 -0
- pytorch_model-00010-of-00028.bin +3 -0
- pytorch_model-00011-of-00028.bin +3 -0
- pytorch_model-00012-of-00028.bin +3 -0
- pytorch_model-00013-of-00028.bin +3 -0
- pytorch_model-00014-of-00028.bin +3 -0
- pytorch_model-00015-of-00028.bin +3 -0
- pytorch_model-00016-of-00028.bin +3 -0
- pytorch_model-00017-of-00028.bin +3 -0
- pytorch_model-00018-of-00028.bin +3 -0
- pytorch_model-00019-of-00028.bin +3 -0
- pytorch_model-00020-of-00028.bin +3 -0
- pytorch_model-00021-of-00028.bin +3 -0
- pytorch_model-00022-of-00028.bin +3 -0
- pytorch_model-00023-of-00028.bin +3 -0
- pytorch_model-00024-of-00028.bin +3 -0
- pytorch_model-00025-of-00028.bin +3 -0
- pytorch_model-00026-of-00028.bin +3 -0
- pytorch_model-00027-of-00028.bin +3 -0
- pytorch_model-00028-of-00028.bin +3 -0
- pytorch_model.bin.index.json +370 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ehartford/WizardLM-13B-V1.0-Uncensored",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"max_sequence_length": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 40,
|
16 |
+
"num_hidden_layers": 40,
|
17 |
+
"num_key_value_heads": 40,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.32.0.dev0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.32.0.dev0"
|
7 |
+
}
|
pytorch_model-00001-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da1b13457e7f2914d48e7c26e32c36c38f46c842aab07a3be48b9f1fc7d7a410
|
3 |
+
size 1924181635
|
pytorch_model-00002-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60b8e147fcb0ddb899342e5fd319401dd0caf0853ed674bbe57aec625036de47
|
3 |
+
size 1971368843
|
pytorch_model-00003-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa25180d3d2bc477c86904effa081e404d5376bef3ec97b9dc757295e06003c4
|
3 |
+
size 1939952523
|
pytorch_model-00004-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15b436154373e8ccd16744aec9394074744ff971d31cc9897ee35b80ddadb35e
|
3 |
+
size 1866510905
|
pytorch_model-00005-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcdb29577b5d97a471ff2854531e84ecda9276a0185b59bba202e5403e41a449
|
3 |
+
size 1939952523
|
pytorch_model-00006-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4b4d3cc0d3b7667c0329e08f4e8da491681b51c2cc3ea19662b0a7b2a4fbf5d
|
3 |
+
size 1866510905
|
pytorch_model-00007-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9217fc3f6b94de3b53269f95a7b457edadffced02a3615722ad1685978ce9900
|
3 |
+
size 1939952523
|
pytorch_model-00008-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d16bbff47fb7a001450d1c4a1df53dfae50bfbcb6bc370a68876304117401e6a
|
3 |
+
size 1866510905
|
pytorch_model-00009-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b2017ae7d5af3a0e50a1170a7861480e7fce48f43f3391936bf099983f1dc77
|
3 |
+
size 1939952523
|
pytorch_model-00010-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:071cc6664e6dc71ec9dfe92be8d6be978bfa7e15fa6a59dc2758b77f1c23c52a
|
3 |
+
size 1866510905
|
pytorch_model-00011-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9da252654431c53cc9f09c31254613a52b7506d56b3f253fd748f434f13201fa
|
3 |
+
size 1939952523
|
pytorch_model-00012-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54821593c2f4eb66f2d0b015defda65e8b3d50609f9a05102e95456bdc27f8dc
|
3 |
+
size 1866510905
|
pytorch_model-00013-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aca2cd9d1ccc930e02bb78c9052a96307c335662d09a145e53cb7d05aed7dce
|
3 |
+
size 1939952523
|
pytorch_model-00014-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea91f0498043880295e8e56dd9bde81d3bcafddfd0d8062e7e31fa0e93ebe9c8
|
3 |
+
size 1866510905
|
pytorch_model-00015-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5788a42470985eede2e48dd34ba0b01fccc9b7bcdf3efab102de49f3e04d1e7f
|
3 |
+
size 1939952523
|
pytorch_model-00016-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2cf9b99f0f06fd4797eaa7180d8e41c30997dd32bad6e1e0e24c02a4ad0dd3b
|
3 |
+
size 1866510905
|
pytorch_model-00017-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c390420ebc122579044a6051e63f5d596af90b9cb2c7cd46df7aa2bd30b7fcbd
|
3 |
+
size 1939952523
|
pytorch_model-00018-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b6c273c0d22e909a95ef2d04a3a9996312051cc6710a187a6bdf0aeff7c5d1e
|
3 |
+
size 1866510905
|
pytorch_model-00019-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23194402f8d6881f4d34899c93537a1c082974e566b1f092a88fa43755b94635
|
3 |
+
size 1939952523
|
pytorch_model-00020-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccf6e901ef21359986c7e11aea1efb678d6bda237825ecb6f5249813269dc6b3
|
3 |
+
size 1866510905
|
pytorch_model-00021-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34c251e02bf0717a1ff4005ab15fc62419445d0c6746552b2636117b942859d8
|
3 |
+
size 1939952523
|
pytorch_model-00022-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d91344a8994567a61609b8aff932a957716e796b01c76f08156b7f4356aa55d
|
3 |
+
size 1866510905
|
pytorch_model-00023-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8525d544305ef1d285443e4a4a7110807c308acbfdb1db3f59dce7eedf0966d
|
3 |
+
size 1939952523
|
pytorch_model-00024-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3148cc808486cca94e867b414aa648c176e36838dd49d0f2830e0b7ed02ed8df
|
3 |
+
size 1866510905
|
pytorch_model-00025-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec80ce6c321746b43a9e72f04fdd0dfa26bf94b39634db57c9bece39a07cd5f7
|
3 |
+
size 1939952523
|
pytorch_model-00026-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c1f922c5b4ee3292b0c9366f2e17011edcf6b6145b7c22649dfa8c94e4bcd0f
|
3 |
+
size 1866510905
|
pytorch_model-00027-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30b998ba463e2dca44c4641923d166cf18f4f27d9011168472f099cd9916c6f3
|
3 |
+
size 1835115339
|
pytorch_model-00028-of-00028.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa40cc408af69bed8e3ca948e1904f0236712d3a973ba6ca5fb7d9210224be1f
|
3 |
+
size 655360938
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 52063457280
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00028-of-00028.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00028.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00028.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00028.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00028.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00028.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00028.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00028.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00028.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00028.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00028.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00028.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00028.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00028.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00028.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00028.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00028.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00028.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00028.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00028.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00008-of-00028.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00008-of-00028.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00028.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00008-of-00028.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008-of-00028.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00028.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00028.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00007-of-00028.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00028.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00028.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00028.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00008-of-00028.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00028.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00028.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00008-of-00028.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00008-of-00028.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008-of-00028.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00008-of-00028.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00009-of-00028.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00009-of-00028.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009-of-00028.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00009-of-00028.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00009-of-00028.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009-of-00028.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009-of-00028.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009-of-00028.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009-of-00028.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00010-of-00028.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00010-of-00028.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00028.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00010-of-00028.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010-of-00028.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00028.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00028.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00009-of-00028.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00028.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00028.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00028.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00010-of-00028.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00028.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00028.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00010-of-00028.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00010-of-00028.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010-of-00028.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00010-of-00028.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00011-of-00028.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00011-of-00028.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011-of-00028.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00011-of-00028.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00011-of-00028.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011-of-00028.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011-of-00028.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011-of-00028.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011-of-00028.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00012-of-00028.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00012-of-00028.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00028.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00012-of-00028.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012-of-00028.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00028.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00028.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00011-of-00028.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00028.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00028.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00028.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00012-of-00028.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00028.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00028.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00012-of-00028.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00012-of-00028.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012-of-00028.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00012-of-00028.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00013-of-00028.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00013-of-00028.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013-of-00028.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00013-of-00028.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00013-of-00028.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00013-of-00028.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013-of-00028.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00013-of-00028.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013-of-00028.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00014-of-00028.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00014-of-00028.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00028.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00014-of-00028.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014-of-00028.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00014-of-00028.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00028.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00013-of-00028.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00014-of-00028.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00028.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00028.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00028.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00028.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00028.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00028.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00028.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00028.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00028.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00028.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00028.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00014-of-00028.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00028.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00028.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00014-of-00028.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00014-of-00028.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014-of-00028.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00014-of-00028.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00015-of-00028.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00015-of-00028.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015-of-00028.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00015-of-00028.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00015-of-00028.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00015-of-00028.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00015-of-00028.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00015-of-00028.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00015-of-00028.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00016-of-00028.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00016-of-00028.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00028.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00016-of-00028.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00016-of-00028.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00016-of-00028.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00028.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00015-of-00028.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00016-of-00028.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00028.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00028.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00016-of-00028.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00028.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00028.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00016-of-00028.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00016-of-00028.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016-of-00028.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00016-of-00028.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00017-of-00028.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00017-of-00028.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00017-of-00028.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00017-of-00028.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00017-of-00028.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00017-of-00028.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00017-of-00028.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00017-of-00028.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00017-of-00028.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00018-of-00028.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00018-of-00028.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00028.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00018-of-00028.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00018-of-00028.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00018-of-00028.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00028.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00017-of-00028.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00018-of-00028.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00019-of-00028.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00019-of-00028.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00018-of-00028.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00019-of-00028.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00019-of-00028.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00018-of-00028.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00018-of-00028.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00018-of-00028.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00018-of-00028.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00019-of-00028.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00019-of-00028.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00019-of-00028.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00019-of-00028.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00019-of-00028.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00019-of-00028.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00019-of-00028.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00019-of-00028.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00019-of-00028.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00020-of-00028.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00020-of-00028.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00020-of-00028.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00020-of-00028.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00020-of-00028.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00020-of-00028.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00020-of-00028.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00019-of-00028.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00020-of-00028.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00021-of-00028.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00021-of-00028.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00020-of-00028.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00021-of-00028.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00021-of-00028.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00020-of-00028.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00020-of-00028.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00020-of-00028.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00020-of-00028.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00028.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00028.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00028.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00028.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00028.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00028.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00028.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00028.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00028.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00021-of-00028.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00021-of-00028.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00021-of-00028.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00021-of-00028.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00021-of-00028.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00021-of-00028.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00021-of-00028.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00021-of-00028.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00021-of-00028.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00022-of-00028.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00022-of-00028.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00022-of-00028.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00022-of-00028.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00022-of-00028.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00022-of-00028.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00022-of-00028.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00021-of-00028.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00022-of-00028.bin",
|
242 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00023-of-00028.bin",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00023-of-00028.bin",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00022-of-00028.bin",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00023-of-00028.bin",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00023-of-00028.bin",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00022-of-00028.bin",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00022-of-00028.bin",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00022-of-00028.bin",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00022-of-00028.bin",
|
251 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00023-of-00028.bin",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00023-of-00028.bin",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00023-of-00028.bin",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00023-of-00028.bin",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00023-of-00028.bin",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00023-of-00028.bin",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00023-of-00028.bin",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00023-of-00028.bin",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00023-of-00028.bin",
|
260 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00024-of-00028.bin",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00024-of-00028.bin",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00024-of-00028.bin",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00024-of-00028.bin",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00024-of-00028.bin",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00024-of-00028.bin",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00024-of-00028.bin",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00023-of-00028.bin",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00024-of-00028.bin",
|
269 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00025-of-00028.bin",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00025-of-00028.bin",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00024-of-00028.bin",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00025-of-00028.bin",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00025-of-00028.bin",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00024-of-00028.bin",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00024-of-00028.bin",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00024-of-00028.bin",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00024-of-00028.bin",
|
278 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00025-of-00028.bin",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00025-of-00028.bin",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00025-of-00028.bin",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00025-of-00028.bin",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00025-of-00028.bin",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00025-of-00028.bin",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00025-of-00028.bin",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00025-of-00028.bin",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00025-of-00028.bin",
|
287 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00026-of-00028.bin",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00026-of-00028.bin",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00026-of-00028.bin",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00026-of-00028.bin",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00026-of-00028.bin",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00026-of-00028.bin",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00026-of-00028.bin",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00025-of-00028.bin",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00026-of-00028.bin",
|
296 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00027-of-00028.bin",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00027-of-00028.bin",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00026-of-00028.bin",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00027-of-00028.bin",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00027-of-00028.bin",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00026-of-00028.bin",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00026-of-00028.bin",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00026-of-00028.bin",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00026-of-00028.bin",
|
305 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00027-of-00028.bin",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00027-of-00028.bin",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00027-of-00028.bin",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00027-of-00028.bin",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00027-of-00028.bin",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00027-of-00028.bin",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00027-of-00028.bin",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00027-of-00028.bin",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00027-of-00028.bin",
|
314 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00028.bin",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00028.bin",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00028.bin",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00028.bin",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00028.bin",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00028.bin",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00028.bin",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00028.bin",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00028.bin",
|
323 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00028.bin",
|
324 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00028.bin",
|
325 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00004-of-00028.bin",
|
326 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00028.bin",
|
327 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00028.bin",
|
328 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00028.bin",
|
329 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00028.bin",
|
330 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00028.bin",
|
331 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00028.bin",
|
332 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00005-of-00028.bin",
|
333 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00005-of-00028.bin",
|
334 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00028.bin",
|
335 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00005-of-00028.bin",
|
336 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00005-of-00028.bin",
|
337 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00028.bin",
|
338 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00028.bin",
|
339 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00028.bin",
|
340 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00028.bin",
|
341 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00006-of-00028.bin",
|
342 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00028.bin",
|
343 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00028.bin",
|
344 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00006-of-00028.bin",
|
345 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006-of-00028.bin",
|
346 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00028.bin",
|
347 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00028.bin",
|
348 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00005-of-00028.bin",
|
349 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00028.bin",
|
350 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00028.bin",
|
351 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00028.bin",
|
352 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00006-of-00028.bin",
|
353 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00028.bin",
|
354 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00028.bin",
|
355 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006-of-00028.bin",
|
356 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006-of-00028.bin",
|
357 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00028.bin",
|
358 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006-of-00028.bin",
|
359 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00007-of-00028.bin",
|
360 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00007-of-00028.bin",
|
361 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007-of-00028.bin",
|
362 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00007-of-00028.bin",
|
363 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00007-of-00028.bin",
|
364 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00028.bin",
|
365 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007-of-00028.bin",
|
366 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00028.bin",
|
367 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00028.bin",
|
368 |
+
"model.norm.weight": "pytorch_model-00027-of-00028.bin"
|
369 |
+
}
|
370 |
+
}
|