new5558 commited on
Commit
f94390d
·
1 Parent(s): 3f5a902

Upload LlamaForCausalLM

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/project/lt200056-opgpth/boss/stanford_alpaca/llama_2_7b_fixed_resized",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -21,7 +21,7 @@
21
  "rope_scaling": null,
22
  "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
- "torch_dtype": "bfloat16",
25
  "transformers_version": "4.33.1",
26
  "use_cache": true,
27
  "vocab_size": 56554
 
1
  {
2
+ "_name_or_path": "/project/lt200056-opgpth/weight_llama_2_finetune_7b_512_th100/checkpoint-2750/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
21
  "rope_scaling": null,
22
  "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
  "transformers_version": "4.33.1",
26
  "use_cache": true,
27
  "vocab_size": 56554
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": "4.33.1"
7
+ }
pytorch_model-00001-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acdd5d111de7c4450412d2b3ebbefc4d323500b262a2a7e439271e6412331037
3
+ size 993690875
pytorch_model-00002-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c17066cfaf420abfb5c5edd5f719855537a4ea4582fb52c15d75088a5f452dc
3
+ size 1010864423
pytorch_model-00003-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf1f0249de63cb3d093cc1ec10d3257d8c7d289500a0347a11d829b9d766d30
3
+ size 989892227
pytorch_model-00004-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ed5ef6aaa1d3240f89d53eae0b700c791a57b8ab3124e417b6972fe37965b6
3
+ size 989892227
pytorch_model-00005-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b552280e2b20c8c977f11205353b299f93a4734a17a02ab19d6df186ccae571e
3
+ size 989925671
pytorch_model-00006-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c0f511f4168bbb717153982615d8ae362ca6372606ef2f945a64eb533a7d1a
3
+ size 1010864423
pytorch_model-00007-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ef8cc6d6a4247e26db6437831be105e93fb216f201cc8dea4ef023d6f3856f
3
+ size 876646019
pytorch_model-00008-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15b6e620bfc348ab4ac7596ed8f6cfef1e5409ea035be5acfd3e267d50c94af7
3
+ size 989892227
pytorch_model-00009-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11f1128cac57ff782590d6212d309363bb745b6e2e4deea10f4b7aa6fce35ad
3
+ size 989892227
pytorch_model-00010-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca817238d298a241c69d5b7da4186ccf996995ea1224d4ea78faea31e996433b
3
+ size 989925671
pytorch_model-00011-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab81c2058d04b01cd54c699ddc1f85410c2ea6dd5b697f08842237c3341cd70
3
+ size 1010864423
pytorch_model-00012-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c001488ba370427d6e131aadfa628aa7efe7574098114400e005da10aee54de
3
+ size 876646083
pytorch_model-00013-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f9a70a930efacc336c6d54ac09a93ff2f67fb0edd218b00c259300b6ef6b50
3
+ size 989892291
pytorch_model-00014-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe510b60c8d96afa4e01838b3797663f57386f07feedf6be96929e62769aa85
3
+ size 989892227
pytorch_model-00015-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccbd4d83dcaa737fcfa07b3da74330b694e78a24caad31ac8218ced80998d9cb
3
+ size 989925671
pytorch_model-00016-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5196947fefc10b829105b97e66b3bf8444c4fb517b4e0ee9803e7899cb5d08f6
3
+ size 1010864423
pytorch_model-00017-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3740bba7ff1b889a79d1a54720cd70c5899b2ccd154c63080bb9346615438cc2
3
+ size 876646083
pytorch_model-00018-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c496fa6e950bd56d325355a78a229944404b376480c945533e1eed2bfe6705
3
+ size 989892291
pytorch_model-00019-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20636364164dd56b90f9405956e954426c1ffd10e765a43521b497f43cba30a
3
+ size 989892227
pytorch_model-00020-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d92ad28d86c1c649435c385aa60ba6996a383d943dbfc6acb00ed9cec5abc81f
3
+ size 989925671
pytorch_model-00021-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc44e8525e3cdb1e7a3e3a521f99b29fe6558c1bd29ed408c32ab93ed528f77
3
+ size 1010864423
pytorch_model-00022-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68c9f74fd36e1a4bc119ba5ab4d81de853ed14212ee17fe0a1ac23a41748ef4
3
+ size 876646083
pytorch_model-00023-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2f9be349c6a1009e76724900d03923b69aee4254f6909e52aa631bfc0b98d1
3
+ size 989892291
pytorch_model-00024-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f014a1991d02f04f7d1da5093c5784e146d5cba1863f8c2275bf8e7e655eeef3
3
+ size 989892227
pytorch_model-00025-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d17e60391f237a5b01eaa5131d7d9262b3f926bc73a2f5ceed9bed9d10cec9
3
+ size 989925671
pytorch_model-00026-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf043e55622ec716f4f46b48814eb65cb9313558cdd6513f12bbac28ef916c5
3
+ size 1010864423
pytorch_model-00027-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71bc29e1be57308f23bbee18f82c1d81e2560ed56ee11ad0f5962ab0b6cad7ff
3
+ size 876646083
pytorch_model-00028-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9c7d76bfc341614f63136ccb4a6aa2697339839ba898128417119901b5ed35
3
+ size 541116863
pytorch_model-00029-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eebe5755215b3681ee873e523fd561383d31d0bd2c5dc49c8c2fa7e6cccff00
3
+ size 926581674
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27758247936
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00029-of-00029.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00029.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
296
+ "model.norm.weight": "pytorch_model-00028-of-00029.bin"
297
+ }
298
+ }