Hugging Face's logo

NbAiLab
/
nb-gpt-j-6B-torgersen-alpaca

Text Generation
Transformers
PyTorch
Safetensors
gptj
Inference Endpoints
Model card Files Community
versae commited on
Commit
f71b5cc
•
1 Parent(s): 1eddcb5

PyTorch and SafeTensors shards

Browse files
Files changed (16) hide show
  1. added_tokens.json +145 -0
  2. config.json +40 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. model-00001-of-00003.safetensors +3 -0
  6. model-00002-of-00003.safetensors +3 -0
  7. model-00003-of-00003.safetensors +3 -0
  8. model.safetensors.index.json +348 -0
  9. pytorch_model-00001-of-00003.bin +3 -0
  10. pytorch_model-00002-of-00003.bin +3 -0
  11. pytorch_model-00003-of-00003.bin +3 -0
  12. pytorch_model.bin.index.json +348 -0
  13. special_tokens_map.json +23 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +31 -0
  16. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|extratoken_100|>": 50356,
3
+ "<|extratoken_101|>": 50357,
4
+ "<|extratoken_102|>": 50358,
5
+ "<|extratoken_103|>": 50359,
6
+ "<|extratoken_104|>": 50360,
7
+ "<|extratoken_105|>": 50361,
8
+ "<|extratoken_106|>": 50362,
9
+ "<|extratoken_107|>": 50363,
10
+ "<|extratoken_108|>": 50364,
11
+ "<|extratoken_109|>": 50365,
12
+ "<|extratoken_10|>": 50266,
13
+ "<|extratoken_110|>": 50366,
14
+ "<|extratoken_111|>": 50367,
15
+ "<|extratoken_112|>": 50368,
16
+ "<|extratoken_113|>": 50369,
17
+ "<|extratoken_114|>": 50370,
18
+ "<|extratoken_115|>": 50371,
19
+ "<|extratoken_116|>": 50372,
20
+ "<|extratoken_117|>": 50373,
21
+ "<|extratoken_118|>": 50374,
22
+ "<|extratoken_119|>": 50375,
23
+ "<|extratoken_11|>": 50267,
24
+ "<|extratoken_120|>": 50376,
25
+ "<|extratoken_121|>": 50377,
26
+ "<|extratoken_122|>": 50378,
27
+ "<|extratoken_123|>": 50379,
28
+ "<|extratoken_124|>": 50380,
29
+ "<|extratoken_125|>": 50381,
30
+ "<|extratoken_126|>": 50382,
31
+ "<|extratoken_127|>": 50383,
32
+ "<|extratoken_128|>": 50384,
33
+ "<|extratoken_129|>": 50385,
34
+ "<|extratoken_12|>": 50268,
35
+ "<|extratoken_130|>": 50386,
36
+ "<|extratoken_131|>": 50387,
37
+ "<|extratoken_132|>": 50388,
38
+ "<|extratoken_133|>": 50389,
39
+ "<|extratoken_134|>": 50390,
40
+ "<|extratoken_135|>": 50391,
41
+ "<|extratoken_136|>": 50392,
42
+ "<|extratoken_137|>": 50393,
43
+ "<|extratoken_138|>": 50394,
44
+ "<|extratoken_139|>": 50395,
45
+ "<|extratoken_13|>": 50269,
46
+ "<|extratoken_140|>": 50396,
47
+ "<|extratoken_141|>": 50397,
48
+ "<|extratoken_142|>": 50398,
49
+ "<|extratoken_143|>": 50399,
50
+ "<|extratoken_14|>": 50270,
51
+ "<|extratoken_15|>": 50271,
52
+ "<|extratoken_16|>": 50272,
53
+ "<|extratoken_17|>": 50273,
54
+ "<|extratoken_18|>": 50274,
55
+ "<|extratoken_19|>": 50275,
56
+ "<|extratoken_1|>": 50257,
57
+ "<|extratoken_20|>": 50276,
58
+ "<|extratoken_21|>": 50277,
59
+ "<|extratoken_22|>": 50278,
60
+ "<|extratoken_23|>": 50279,
61
+ "<|extratoken_24|>": 50280,
62
+ "<|extratoken_25|>": 50281,
63
+ "<|extratoken_26|>": 50282,
64
+ "<|extratoken_27|>": 50283,
65
+ "<|extratoken_28|>": 50284,
66
+ "<|extratoken_29|>": 50285,
67
+ "<|extratoken_2|>": 50258,
68
+ "<|extratoken_30|>": 50286,
69
+ "<|extratoken_31|>": 50287,
70
+ "<|extratoken_32|>": 50288,
71
+ "<|extratoken_33|>": 50289,
72
+ "<|extratoken_34|>": 50290,
73
+ "<|extratoken_35|>": 50291,
74
+ "<|extratoken_36|>": 50292,
75
+ "<|extratoken_37|>": 50293,
76
+ "<|extratoken_38|>": 50294,
77
+ "<|extratoken_39|>": 50295,
78
+ "<|extratoken_3|>": 50259,
79
+ "<|extratoken_40|>": 50296,
80
+ "<|extratoken_41|>": 50297,
81
+ "<|extratoken_42|>": 50298,
82
+ "<|extratoken_43|>": 50299,
83
+ "<|extratoken_44|>": 50300,
84
+ "<|extratoken_45|>": 50301,
85
+ "<|extratoken_46|>": 50302,
86
+ "<|extratoken_47|>": 50303,
87
+ "<|extratoken_48|>": 50304,
88
+ "<|extratoken_49|>": 50305,
89
+ "<|extratoken_4|>": 50260,
90
+ "<|extratoken_50|>": 50306,
91
+ "<|extratoken_51|>": 50307,
92
+ "<|extratoken_52|>": 50308,
93
+ "<|extratoken_53|>": 50309,
94
+ "<|extratoken_54|>": 50310,
95
+ "<|extratoken_55|>": 50311,
96
+ "<|extratoken_56|>": 50312,
97
+ "<|extratoken_57|>": 50313,
98
+ "<|extratoken_58|>": 50314,
99
+ "<|extratoken_59|>": 50315,
100
+ "<|extratoken_5|>": 50261,
101
+ "<|extratoken_60|>": 50316,
102
+ "<|extratoken_61|>": 50317,
103
+ "<|extratoken_62|>": 50318,
104
+ "<|extratoken_63|>": 50319,
105
+ "<|extratoken_64|>": 50320,
106
+ "<|extratoken_65|>": 50321,
107
+ "<|extratoken_66|>": 50322,
108
+ "<|extratoken_67|>": 50323,
109
+ "<|extratoken_68|>": 50324,
110
+ "<|extratoken_69|>": 50325,
111
+ "<|extratoken_6|>": 50262,
112
+ "<|extratoken_70|>": 50326,
113
+ "<|extratoken_71|>": 50327,
114
+ "<|extratoken_72|>": 50328,
115
+ "<|extratoken_73|>": 50329,
116
+ "<|extratoken_74|>": 50330,
117
+ "<|extratoken_75|>": 50331,
118
+ "<|extratoken_76|>": 50332,
119
+ "<|extratoken_77|>": 50333,
120
+ "<|extratoken_78|>": 50334,
121
+ "<|extratoken_79|>": 50335,
122
+ "<|extratoken_7|>": 50263,
123
+ "<|extratoken_80|>": 50336,
124
+ "<|extratoken_81|>": 50337,
125
+ "<|extratoken_82|>": 50338,
126
+ "<|extratoken_83|>": 50339,
127
+ "<|extratoken_84|>": 50340,
128
+ "<|extratoken_85|>": 50341,
129
+ "<|extratoken_86|>": 50342,
130
+ "<|extratoken_87|>": 50343,
131
+ "<|extratoken_88|>": 50344,
132
+ "<|extratoken_89|>": 50345,
133
+ "<|extratoken_8|>": 50264,
134
+ "<|extratoken_90|>": 50346,
135
+ "<|extratoken_91|>": 50347,
136
+ "<|extratoken_92|>": 50348,
137
+ "<|extratoken_93|>": 50349,
138
+ "<|extratoken_94|>": 50350,
139
+ "<|extratoken_95|>": 50351,
140
+ "<|extratoken_96|>": 50352,
141
+ "<|extratoken_97|>": 50353,
142
+ "<|extratoken_98|>": 50354,
143
+ "<|extratoken_99|>": 50355,
144
+ "<|extratoken_9|>": 50265
145
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gptj",
15
+ "n_embd": 4096,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 28,
19
+ "n_positions": 2048,
20
+ "resid_pdrop": 0.0,
21
+ "rotary_dim": 64,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50,
31
+ "temperature": 1.0
32
+ }
33
+ },
34
+ "tie_word_embeddings": false,
35
+ "tokenizer_class": "GPT2Tokenizer",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.27.4",
38
+ "use_cache": true,
39
+ "vocab_size": 50400
40
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.27.4"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba51c1e6683885813f5714d44216dbc04ccc03b84fdb2843dc81660116cc86e
3
+ size 10004200288
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894490c2750d589281a22f53d5d708593578ca6d04cbd0ac77b9355249feff9e
3
+ size 9983901176
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd1aacb76d79ffbea2d8bf36b544e2da10cf4feb5a8a411cc19499a2de43cc1
3
+ size 4332907072
model.safetensors.index.json ADDED
@@ -0,0 +1,348 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24218211312.0
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "model-00003-of-00003.safetensors",
7
+ "lm_head.weight": "model-00003-of-00003.safetensors",
8
+ "transformer.h.0.attn.bias": "model-00001-of-00003.safetensors",
9
+ "transformer.h.0.attn.k_proj.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.0.attn.masked_bias": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.attn.out_proj.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.h.0.attn.q_proj.weight": "model-00001-of-00003.safetensors",
13
+ "transformer.h.0.attn.v_proj.weight": "model-00001-of-00003.safetensors",
14
+ "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
15
+ "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.h.0.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
17
+ "transformer.h.0.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.h.0.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
19
+ "transformer.h.0.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.h.1.attn.bias": "model-00001-of-00003.safetensors",
21
+ "transformer.h.1.attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.1.attn.masked_bias": "model-00001-of-00003.safetensors",
23
+ "transformer.h.1.attn.out_proj.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.1.attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "transformer.h.1.attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
27
+ "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
28
+ "transformer.h.1.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
29
+ "transformer.h.1.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.h.1.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
31
+ "transformer.h.1.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
32
+ "transformer.h.10.attn.bias": "model-00001-of-00003.safetensors",
33
+ "transformer.h.10.attn.k_proj.weight": "model-00001-of-00003.safetensors",
34
+ "transformer.h.10.attn.masked_bias": "model-00001-of-00003.safetensors",
35
+ "transformer.h.10.attn.out_proj.weight": "model-00001-of-00003.safetensors",
36
+ "transformer.h.10.attn.q_proj.weight": "model-00001-of-00003.safetensors",
37
+ "transformer.h.10.attn.v_proj.weight": "model-00001-of-00003.safetensors",
38
+ "transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
39
+ "transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
40
+ "transformer.h.10.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
41
+ "transformer.h.10.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
42
+ "transformer.h.10.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
43
+ "transformer.h.10.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
44
+ "transformer.h.11.attn.bias": "model-00001-of-00003.safetensors",
45
+ "transformer.h.11.attn.k_proj.weight": "model-00001-of-00003.safetensors",
46
+ "transformer.h.11.attn.masked_bias": "model-00001-of-00003.safetensors",
47
+ "transformer.h.11.attn.out_proj.weight": "model-00001-of-00003.safetensors",
48
+ "transformer.h.11.attn.q_proj.weight": "model-00001-of-00003.safetensors",
49
+ "transformer.h.11.attn.v_proj.weight": "model-00001-of-00003.safetensors",
50
+ "transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
51
+ "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
52
+ "transformer.h.11.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
53
+ "transformer.h.11.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
54
+ "transformer.h.11.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
55
+ "transformer.h.11.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
56
+ "transformer.h.12.attn.bias": "model-00002-of-00003.safetensors",
57
+ "transformer.h.12.attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "transformer.h.12.attn.masked_bias": "model-00002-of-00003.safetensors",
59
+ "transformer.h.12.attn.out_proj.weight": "model-00002-of-00003.safetensors",
60
+ "transformer.h.12.attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "transformer.h.12.attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "transformer.h.12.ln_1.bias": "model-00002-of-00003.safetensors",
63
+ "transformer.h.12.ln_1.weight": "model-00002-of-00003.safetensors",
64
+ "transformer.h.12.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
65
+ "transformer.h.12.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
66
+ "transformer.h.12.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
67
+ "transformer.h.12.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
68
+ "transformer.h.13.attn.bias": "model-00002-of-00003.safetensors",
69
+ "transformer.h.13.attn.k_proj.weight": "model-00002-of-00003.safetensors",
70
+ "transformer.h.13.attn.masked_bias": "model-00002-of-00003.safetensors",
71
+ "transformer.h.13.attn.out_proj.weight": "model-00002-of-00003.safetensors",
72
+ "transformer.h.13.attn.q_proj.weight": "model-00002-of-00003.safetensors",
73
+ "transformer.h.13.attn.v_proj.weight": "model-00002-of-00003.safetensors",
74
+ "transformer.h.13.ln_1.bias": "model-00002-of-00003.safetensors",
75
+ "transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
76
+ "transformer.h.13.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
77
+ "transformer.h.13.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
78
+ "transformer.h.13.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
79
+ "transformer.h.13.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
80
+ "transformer.h.14.attn.bias": "model-00002-of-00003.safetensors",
81
+ "transformer.h.14.attn.k_proj.weight": "model-00002-of-00003.safetensors",
82
+ "transformer.h.14.attn.masked_bias": "model-00002-of-00003.safetensors",
83
+ "transformer.h.14.attn.out_proj.weight": "model-00002-of-00003.safetensors",
84
+ "transformer.h.14.attn.q_proj.weight": "model-00002-of-00003.safetensors",
85
+ "transformer.h.14.attn.v_proj.weight": "model-00002-of-00003.safetensors",
86
+ "transformer.h.14.ln_1.bias": "model-00002-of-00003.safetensors",
87
+ "transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
88
+ "transformer.h.14.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
89
+ "transformer.h.14.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
90
+ "transformer.h.14.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
91
+ "transformer.h.14.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
92
+ "transformer.h.15.attn.bias": "model-00002-of-00003.safetensors",
93
+ "transformer.h.15.attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "transformer.h.15.attn.masked_bias": "model-00002-of-00003.safetensors",
95
+ "transformer.h.15.attn.out_proj.weight": "model-00002-of-00003.safetensors",
96
+ "transformer.h.15.attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "transformer.h.15.attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
99
+ "transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.h.15.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
101
+ "transformer.h.15.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.h.15.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
103
+ "transformer.h.15.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
104
+ "transformer.h.16.attn.bias": "model-00002-of-00003.safetensors",
105
+ "transformer.h.16.attn.k_proj.weight": "model-00002-of-00003.safetensors",
106
+ "transformer.h.16.attn.masked_bias": "model-00002-of-00003.safetensors",
107
+ "transformer.h.16.attn.out_proj.weight": "model-00002-of-00003.safetensors",
108
+ "transformer.h.16.attn.q_proj.weight": "model-00002-of-00003.safetensors",
109
+ "transformer.h.16.attn.v_proj.weight": "model-00002-of-00003.safetensors",
110
+ "transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
111
+ "transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
112
+ "transformer.h.16.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
113
+ "transformer.h.16.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
114
+ "transformer.h.16.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
115
+ "transformer.h.16.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
116
+ "transformer.h.17.attn.bias": "model-00002-of-00003.safetensors",
117
+ "transformer.h.17.attn.k_proj.weight": "model-00002-of-00003.safetensors",
118
+ "transformer.h.17.attn.masked_bias": "model-00002-of-00003.safetensors",
119
+ "transformer.h.17.attn.out_proj.weight": "model-00002-of-00003.safetensors",
120
+ "transformer.h.17.attn.q_proj.weight": "model-00002-of-00003.safetensors",
121
+ "transformer.h.17.attn.v_proj.weight": "model-00002-of-00003.safetensors",
122
+ "transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
123
+ "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
124
+ "transformer.h.17.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
125
+ "transformer.h.17.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
126
+ "transformer.h.17.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
127
+ "transformer.h.17.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
128
+ "transformer.h.18.attn.bias": "model-00002-of-00003.safetensors",
129
+ "transformer.h.18.attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "transformer.h.18.attn.masked_bias": "model-00002-of-00003.safetensors",
131
+ "transformer.h.18.attn.out_proj.weight": "model-00002-of-00003.safetensors",
132
+ "transformer.h.18.attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "transformer.h.18.attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
135
+ "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
136
+ "transformer.h.18.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
137
+ "transformer.h.18.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
138
+ "transformer.h.18.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
139
+ "transformer.h.18.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
140
+ "transformer.h.19.attn.bias": "model-00002-of-00003.safetensors",
141
+ "transformer.h.19.attn.k_proj.weight": "model-00002-of-00003.safetensors",
142
+ "transformer.h.19.attn.masked_bias": "model-00002-of-00003.safetensors",
143
+ "transformer.h.19.attn.out_proj.weight": "model-00002-of-00003.safetensors",
144
+ "transformer.h.19.attn.q_proj.weight": "model-00002-of-00003.safetensors",
145
+ "transformer.h.19.attn.v_proj.weight": "model-00002-of-00003.safetensors",
146
+ "transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
147
+ "transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
148
+ "transformer.h.19.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
149
+ "transformer.h.19.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
150
+ "transformer.h.19.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
151
+ "transformer.h.19.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
152
+ "transformer.h.2.attn.bias": "model-00001-of-00003.safetensors",
153
+ "transformer.h.2.attn.k_proj.weight": "model-00001-of-00003.safetensors",
154
+ "transformer.h.2.attn.masked_bias": "model-00001-of-00003.safetensors",
155
+ "transformer.h.2.attn.out_proj.weight": "model-00001-of-00003.safetensors",
156
+ "transformer.h.2.attn.q_proj.weight": "model-00001-of-00003.safetensors",
157
+ "transformer.h.2.attn.v_proj.weight": "model-00001-of-00003.safetensors",
158
+ "transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
159
+ "transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
160
+ "transformer.h.2.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
161
+ "transformer.h.2.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
162
+ "transformer.h.2.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
163
+ "transformer.h.2.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
164
+ "transformer.h.20.attn.bias": "model-00002-of-00003.safetensors",
165
+ "transformer.h.20.attn.k_proj.weight": "model-00002-of-00003.safetensors",
166
+ "transformer.h.20.attn.masked_bias": "model-00002-of-00003.safetensors",
167
+ "transformer.h.20.attn.out_proj.weight": "model-00002-of-00003.safetensors",
168
+ "transformer.h.20.attn.q_proj.weight": "model-00002-of-00003.safetensors",
169
+ "transformer.h.20.attn.v_proj.weight": "model-00002-of-00003.safetensors",
170
+ "transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
171
+ "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
172
+ "transformer.h.20.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
173
+ "transformer.h.20.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
174
+ "transformer.h.20.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
175
+ "transformer.h.20.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
176
+ "transformer.h.21.attn.bias": "model-00002-of-00003.safetensors",
177
+ "transformer.h.21.attn.k_proj.weight": "model-00002-of-00003.safetensors",
178
+ "transformer.h.21.attn.masked_bias": "model-00002-of-00003.safetensors",
179
+ "transformer.h.21.attn.out_proj.weight": "model-00002-of-00003.safetensors",
180
+ "transformer.h.21.attn.q_proj.weight": "model-00002-of-00003.safetensors",
181
+ "transformer.h.21.attn.v_proj.weight": "model-00002-of-00003.safetensors",
182
+ "transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
183
+ "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
184
+ "transformer.h.21.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
185
+ "transformer.h.21.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
186
+ "transformer.h.21.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
187
+ "transformer.h.21.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
188
+ "transformer.h.22.attn.bias": "model-00002-of-00003.safetensors",
189
+ "transformer.h.22.attn.k_proj.weight": "model-00002-of-00003.safetensors",
190
+ "transformer.h.22.attn.masked_bias": "model-00002-of-00003.safetensors",
191
+ "transformer.h.22.attn.out_proj.weight": "model-00002-of-00003.safetensors",
192
+ "transformer.h.22.attn.q_proj.weight": "model-00002-of-00003.safetensors",
193
+ "transformer.h.22.attn.v_proj.weight": "model-00002-of-00003.safetensors",
194
+ "transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
195
+ "transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
196
+ "transformer.h.22.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
197
+ "transformer.h.22.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
198
+ "transformer.h.22.mlp.fc_out.bias": "model-00002-of-00003.safetensors",
199
+ "transformer.h.22.mlp.fc_out.weight": "model-00002-of-00003.safetensors",
200
+ "transformer.h.23.attn.bias": "model-00002-of-00003.safetensors",
201
+ "transformer.h.23.attn.k_proj.weight": "model-00002-of-00003.safetensors",
202
+ "transformer.h.23.attn.masked_bias": "model-00002-of-00003.safetensors",
203
+ "transformer.h.23.attn.out_proj.weight": "model-00002-of-00003.safetensors",
204
+ "transformer.h.23.attn.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "transformer.h.23.attn.v_proj.weight": "model-00002-of-00003.safetensors",
206
+ "transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
207
+ "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
208
+ "transformer.h.23.mlp.fc_in.bias": "model-00002-of-00003.safetensors",
209
+ "transformer.h.23.mlp.fc_in.weight": "model-00002-of-00003.safetensors",
210
+ "transformer.h.23.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
211
+ "transformer.h.23.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
212
+ "transformer.h.24.attn.bias": "model-00003-of-00003.safetensors",
213
+ "transformer.h.24.attn.k_proj.weight": "model-00003-of-00003.safetensors",
214
+ "transformer.h.24.attn.masked_bias": "model-00003-of-00003.safetensors",
215
+ "transformer.h.24.attn.out_proj.weight": "model-00003-of-00003.safetensors",
216
+ "transformer.h.24.attn.q_proj.weight": "model-00003-of-00003.safetensors",
217
+ "transformer.h.24.attn.v_proj.weight": "model-00003-of-00003.safetensors",
218
+ "transformer.h.24.ln_1.bias": "model-00003-of-00003.safetensors",
219
+ "transformer.h.24.ln_1.weight": "model-00003-of-00003.safetensors",
220
+ "transformer.h.24.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
221
+ "transformer.h.24.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
222
+ "transformer.h.24.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
223
+ "transformer.h.24.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
224
+ "transformer.h.25.attn.bias": "model-00003-of-00003.safetensors",
225
+ "transformer.h.25.attn.k_proj.weight": "model-00003-of-00003.safetensors",
226
+ "transformer.h.25.attn.masked_bias": "model-00003-of-00003.safetensors",
227
+ "transformer.h.25.attn.out_proj.weight": "model-00003-of-00003.safetensors",
228
+ "transformer.h.25.attn.q_proj.weight": "model-00003-of-00003.safetensors",
229
+ "transformer.h.25.attn.v_proj.weight": "model-00003-of-00003.safetensors",
230
+ "transformer.h.25.ln_1.bias": "model-00003-of-00003.safetensors",
231
+ "transformer.h.25.ln_1.weight": "model-00003-of-00003.safetensors",
232
+ "transformer.h.25.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
233
+ "transformer.h.25.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
234
+ "transformer.h.25.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
235
+ "transformer.h.25.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
236
+ "transformer.h.26.attn.bias": "model-00003-of-00003.safetensors",
237
+ "transformer.h.26.attn.k_proj.weight": "model-00003-of-00003.safetensors",
238
+ "transformer.h.26.attn.masked_bias": "model-00003-of-00003.safetensors",
239
+ "transformer.h.26.attn.out_proj.weight": "model-00003-of-00003.safetensors",
240
+ "transformer.h.26.attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "transformer.h.26.attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "transformer.h.26.ln_1.bias": "model-00003-of-00003.safetensors",
243
+ "transformer.h.26.ln_1.weight": "model-00003-of-00003.safetensors",
244
+ "transformer.h.26.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
245
+ "transformer.h.26.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
246
+ "transformer.h.26.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
247
+ "transformer.h.26.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
248
+ "transformer.h.27.attn.bias": "model-00003-of-00003.safetensors",
249
+ "transformer.h.27.attn.k_proj.weight": "model-00003-of-00003.safetensors",
250
+ "transformer.h.27.attn.masked_bias": "model-00003-of-00003.safetensors",
251
+ "transformer.h.27.attn.out_proj.weight": "model-00003-of-00003.safetensors",
252
+ "transformer.h.27.attn.q_proj.weight": "model-00003-of-00003.safetensors",
253
+ "transformer.h.27.attn.v_proj.weight": "model-00003-of-00003.safetensors",
254
+ "transformer.h.27.ln_1.bias": "model-00003-of-00003.safetensors",
255
+ "transformer.h.27.ln_1.weight": "model-00003-of-00003.safetensors",
256
+ "transformer.h.27.mlp.fc_in.bias": "model-00003-of-00003.safetensors",
257
+ "transformer.h.27.mlp.fc_in.weight": "model-00003-of-00003.safetensors",
258
+ "transformer.h.27.mlp.fc_out.bias": "model-00003-of-00003.safetensors",
259
+ "transformer.h.27.mlp.fc_out.weight": "model-00003-of-00003.safetensors",
260
+ "transformer.h.3.attn.bias": "model-00001-of-00003.safetensors",
261
+ "transformer.h.3.attn.k_proj.weight": "model-00001-of-00003.safetensors",
262
+ "transformer.h.3.attn.masked_bias": "model-00001-of-00003.safetensors",
263
+ "transformer.h.3.attn.out_proj.weight": "model-00001-of-00003.safetensors",
264
+ "transformer.h.3.attn.q_proj.weight": "model-00001-of-00003.safetensors",
265
+ "transformer.h.3.attn.v_proj.weight": "model-00001-of-00003.safetensors",
266
+ "transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
267
+ "transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
268
+ "transformer.h.3.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
269
+ "transformer.h.3.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
270
+ "transformer.h.3.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
271
+ "transformer.h.3.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
272
+ "transformer.h.4.attn.bias": "model-00001-of-00003.safetensors",
273
+ "transformer.h.4.attn.k_proj.weight": "model-00001-of-00003.safetensors",
274
+ "transformer.h.4.attn.masked_bias": "model-00001-of-00003.safetensors",
275
+ "transformer.h.4.attn.out_proj.weight": "model-00001-of-00003.safetensors",
276
+ "transformer.h.4.attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "transformer.h.4.attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
279
+ "transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
280
+ "transformer.h.4.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
281
+ "transformer.h.4.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
282
+ "transformer.h.4.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
283
+ "transformer.h.4.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
284
+ "transformer.h.5.attn.bias": "model-00001-of-00003.safetensors",
285
+ "transformer.h.5.attn.k_proj.weight": "model-00001-of-00003.safetensors",
286
+ "transformer.h.5.attn.masked_bias": "model-00001-of-00003.safetensors",
287
+ "transformer.h.5.attn.out_proj.weight": "model-00001-of-00003.safetensors",
288
+ "transformer.h.5.attn.q_proj.weight": "model-00001-of-00003.safetensors",
289
+ "transformer.h.5.attn.v_proj.weight": "model-00001-of-00003.safetensors",
290
+ "transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
291
+ "transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
292
+ "transformer.h.5.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
293
+ "transformer.h.5.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
294
+ "transformer.h.5.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
295
+ "transformer.h.5.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
296
+ "transformer.h.6.attn.bias": "model-00001-of-00003.safetensors",
297
+ "transformer.h.6.attn.k_proj.weight": "model-00001-of-00003.safetensors",
298
+ "transformer.h.6.attn.masked_bias": "model-00001-of-00003.safetensors",
299
+ "transformer.h.6.attn.out_proj.weight": "model-00001-of-00003.safetensors",
300
+ "transformer.h.6.attn.q_proj.weight": "model-00001-of-00003.safetensors",
301
+ "transformer.h.6.attn.v_proj.weight": "model-00001-of-00003.safetensors",
302
+ "transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
303
+ "transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
304
+ "transformer.h.6.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
305
+ "transformer.h.6.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
306
+ "transformer.h.6.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
307
+ "transformer.h.6.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
308
+ "transformer.h.7.attn.bias": "model-00001-of-00003.safetensors",
309
+ "transformer.h.7.attn.k_proj.weight": "model-00001-of-00003.safetensors",
310
+ "transformer.h.7.attn.masked_bias": "model-00001-of-00003.safetensors",
311
+ "transformer.h.7.attn.out_proj.weight": "model-00001-of-00003.safetensors",
312
+ "transformer.h.7.attn.q_proj.weight": "model-00001-of-00003.safetensors",
313
+ "transformer.h.7.attn.v_proj.weight": "model-00001-of-00003.safetensors",
314
+ "transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
315
+ "transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
316
+ "transformer.h.7.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
317
+ "transformer.h.7.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
318
+ "transformer.h.7.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
319
+ "transformer.h.7.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
320
+ "transformer.h.8.attn.bias": "model-00001-of-00003.safetensors",
321
+ "transformer.h.8.attn.k_proj.weight": "model-00001-of-00003.safetensors",
322
+ "transformer.h.8.attn.masked_bias": "model-00001-of-00003.safetensors",
323
+ "transformer.h.8.attn.out_proj.weight": "model-00001-of-00003.safetensors",
324
+ "transformer.h.8.attn.q_proj.weight": "model-00001-of-00003.safetensors",
325
+ "transformer.h.8.attn.v_proj.weight": "model-00001-of-00003.safetensors",
326
+ "transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
327
+ "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
328
+ "transformer.h.8.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
329
+ "transformer.h.8.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
330
+ "transformer.h.8.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
331
+ "transformer.h.8.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
332
+ "transformer.h.9.attn.bias": "model-00001-of-00003.safetensors",
333
+ "transformer.h.9.attn.k_proj.weight": "model-00001-of-00003.safetensors",
334
+ "transformer.h.9.attn.masked_bias": "model-00001-of-00003.safetensors",
335
+ "transformer.h.9.attn.out_proj.weight": "model-00001-of-00003.safetensors",
336
+ "transformer.h.9.attn.q_proj.weight": "model-00001-of-00003.safetensors",
337
+ "transformer.h.9.attn.v_proj.weight": "model-00001-of-00003.safetensors",
338
+ "transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
339
+ "transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
340
+ "transformer.h.9.mlp.fc_in.bias": "model-00001-of-00003.safetensors",
341
+ "transformer.h.9.mlp.fc_in.weight": "model-00001-of-00003.safetensors",
342
+ "transformer.h.9.mlp.fc_out.bias": "model-00001-of-00003.safetensors",
343
+ "transformer.h.9.mlp.fc_out.weight": "model-00001-of-00003.safetensors",
344
+ "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
345
+ "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
346
+ "transformer.wte.weight": "model-00001-of-00003.safetensors"
347
+ }
348
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58f7e100f105031b4b7ece40bac2ec4855ac8ffd7f00b88b1772126726ffcf8
3
+ size 10004229239
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e702e3d72ee73672908f8c656bd49693facb7397e257f37fb1bdfa6d99b6a64a
3
+ size 9983931181
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5773179c7c5143a105226e4fdc97af35cca48f50194ec8609a1d889c4de0aa8
3
+ size 4332917143
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,348 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24218211312.0
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "pytorch_model-00003-of-00003.bin",
7
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
8
+ "transformer.h.0.attn.bias": "pytorch_model-00001-of-00003.bin",
9
+ "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
11
+ "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
13
+ "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
15
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
16
+ "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
17
+ "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
18
+ "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
19
+ "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
20
+ "transformer.h.1.attn.bias": "pytorch_model-00001-of-00003.bin",
21
+ "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
23
+ "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
27
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
28
+ "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
29
+ "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
30
+ "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
31
+ "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
32
+ "transformer.h.10.attn.bias": "pytorch_model-00001-of-00003.bin",
33
+ "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "transformer.h.10.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
35
+ "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
39
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
40
+ "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
41
+ "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
42
+ "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
43
+ "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
44
+ "transformer.h.11.attn.bias": "pytorch_model-00001-of-00003.bin",
45
+ "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "transformer.h.11.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
47
+ "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
49
+ "transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
51
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
52
+ "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
53
+ "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
54
+ "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
55
+ "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
56
+ "transformer.h.12.attn.bias": "pytorch_model-00002-of-00003.bin",
57
+ "transformer.h.12.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "transformer.h.12.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
59
+ "transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "transformer.h.12.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "transformer.h.12.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00003.bin",
63
+ "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00003.bin",
64
+ "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
65
+ "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
66
+ "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
67
+ "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
68
+ "transformer.h.13.attn.bias": "pytorch_model-00002-of-00003.bin",
69
+ "transformer.h.13.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "transformer.h.13.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
71
+ "transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
72
+ "transformer.h.13.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "transformer.h.13.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00003.bin",
75
+ "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00003.bin",
76
+ "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
77
+ "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
78
+ "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
79
+ "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
80
+ "transformer.h.14.attn.bias": "pytorch_model-00002-of-00003.bin",
81
+ "transformer.h.14.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "transformer.h.14.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
83
+ "transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "transformer.h.14.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "transformer.h.14.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00003.bin",
87
+ "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin",
88
+ "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
89
+ "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
90
+ "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
91
+ "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
92
+ "transformer.h.15.attn.bias": "pytorch_model-00002-of-00003.bin",
93
+ "transformer.h.15.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "transformer.h.15.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
95
+ "transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "transformer.h.15.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
+ "transformer.h.15.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00003.bin",
99
+ "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin",
100
+ "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
101
+ "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
102
+ "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
103
+ "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
104
+ "transformer.h.16.attn.bias": "pytorch_model-00002-of-00003.bin",
105
+ "transformer.h.16.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "transformer.h.16.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
107
+ "transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "transformer.h.16.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "transformer.h.16.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00003.bin",
111
+ "transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
112
+ "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
113
+ "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
114
+ "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
115
+ "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
116
+ "transformer.h.17.attn.bias": "pytorch_model-00002-of-00003.bin",
117
+ "transformer.h.17.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "transformer.h.17.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
119
+ "transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "transformer.h.17.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "transformer.h.17.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00003.bin",
123
+ "transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
124
+ "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
125
+ "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
126
+ "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
127
+ "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
128
+ "transformer.h.18.attn.bias": "pytorch_model-00002-of-00003.bin",
129
+ "transformer.h.18.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
130
+ "transformer.h.18.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
131
+ "transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "transformer.h.18.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "transformer.h.18.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00003.bin",
135
+ "transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
136
+ "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
137
+ "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
138
+ "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
139
+ "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
140
+ "transformer.h.19.attn.bias": "pytorch_model-00002-of-00003.bin",
141
+ "transformer.h.19.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "transformer.h.19.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
143
+ "transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "transformer.h.19.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "transformer.h.19.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00003.bin",
147
+ "transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
148
+ "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
149
+ "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
150
+ "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
151
+ "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
152
+ "transformer.h.2.attn.bias": "pytorch_model-00001-of-00003.bin",
153
+ "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
154
+ "transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
155
+ "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
156
+ "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
157
+ "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
158
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
159
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
160
+ "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
161
+ "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
162
+ "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
163
+ "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
164
+ "transformer.h.20.attn.bias": "pytorch_model-00002-of-00003.bin",
165
+ "transformer.h.20.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "transformer.h.20.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
167
+ "transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "transformer.h.20.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
169
+ "transformer.h.20.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00003.bin",
171
+ "transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
172
+ "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
173
+ "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
174
+ "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
175
+ "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
176
+ "transformer.h.21.attn.bias": "pytorch_model-00002-of-00003.bin",
177
+ "transformer.h.21.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "transformer.h.21.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
179
+ "transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
180
+ "transformer.h.21.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "transformer.h.21.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00003.bin",
183
+ "transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
184
+ "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
185
+ "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
186
+ "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
187
+ "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
188
+ "transformer.h.22.attn.bias": "pytorch_model-00002-of-00003.bin",
189
+ "transformer.h.22.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "transformer.h.22.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
191
+ "transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "transformer.h.22.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
193
+ "transformer.h.22.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00003.bin",
195
+ "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
196
+ "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
197
+ "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
198
+ "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
199
+ "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
200
+ "transformer.h.23.attn.bias": "pytorch_model-00002-of-00003.bin",
201
+ "transformer.h.23.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
202
+ "transformer.h.23.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
203
+ "transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "transformer.h.23.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "transformer.h.23.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00003.bin",
207
+ "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
208
+ "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
209
+ "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
210
+ "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
211
+ "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
212
+ "transformer.h.24.attn.bias": "pytorch_model-00003-of-00003.bin",
213
+ "transformer.h.24.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "transformer.h.24.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
215
+ "transformer.h.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
216
+ "transformer.h.24.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
217
+ "transformer.h.24.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
+ "transformer.h.24.ln_1.bias": "pytorch_model-00003-of-00003.bin",
219
+ "transformer.h.24.ln_1.weight": "pytorch_model-00003-of-00003.bin",
220
+ "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
221
+ "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
222
+ "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
223
+ "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
224
+ "transformer.h.25.attn.bias": "pytorch_model-00003-of-00003.bin",
225
+ "transformer.h.25.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "transformer.h.25.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
227
+ "transformer.h.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "transformer.h.25.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
229
+ "transformer.h.25.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "transformer.h.25.ln_1.bias": "pytorch_model-00003-of-00003.bin",
231
+ "transformer.h.25.ln_1.weight": "pytorch_model-00003-of-00003.bin",
232
+ "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
233
+ "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
234
+ "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
235
+ "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
236
+ "transformer.h.26.attn.bias": "pytorch_model-00003-of-00003.bin",
237
+ "transformer.h.26.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
238
+ "transformer.h.26.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
239
+ "transformer.h.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
240
+ "transformer.h.26.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
+ "transformer.h.26.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00003.bin",
243
+ "transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00003.bin",
244
+ "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
245
+ "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
246
+ "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
247
+ "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
248
+ "transformer.h.27.attn.bias": "pytorch_model-00003-of-00003.bin",
249
+ "transformer.h.27.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "transformer.h.27.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
251
+ "transformer.h.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
252
+ "transformer.h.27.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
253
+ "transformer.h.27.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
254
+ "transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00003.bin",
255
+ "transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00003.bin",
256
+ "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
257
+ "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
258
+ "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
259
+ "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
260
+ "transformer.h.3.attn.bias": "pytorch_model-00001-of-00003.bin",
261
+ "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
262
+ "transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
263
+ "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
264
+ "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
265
+ "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
266
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
267
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
268
+ "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
269
+ "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
270
+ "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
271
+ "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
272
+ "transformer.h.4.attn.bias": "pytorch_model-00001-of-00003.bin",
273
+ "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
+ "transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
275
+ "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
277
+ "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
279
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
280
+ "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
281
+ "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
282
+ "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
283
+ "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
284
+ "transformer.h.5.attn.bias": "pytorch_model-00001-of-00003.bin",
285
+ "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "transformer.h.5.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
287
+ "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
288
+ "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
289
+ "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
291
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
292
+ "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
293
+ "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
294
+ "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
295
+ "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
296
+ "transformer.h.6.attn.bias": "pytorch_model-00001-of-00003.bin",
297
+ "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
298
+ "transformer.h.6.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
299
+ "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
300
+ "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
301
+ "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
302
+ "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
303
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
304
+ "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
305
+ "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
306
+ "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
307
+ "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
308
+ "transformer.h.7.attn.bias": "pytorch_model-00001-of-00003.bin",
309
+ "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
310
+ "transformer.h.7.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
311
+ "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
312
+ "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
313
+ "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
314
+ "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
315
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
316
+ "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
317
+ "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
318
+ "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
319
+ "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
320
+ "transformer.h.8.attn.bias": "pytorch_model-00001-of-00003.bin",
321
+ "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "transformer.h.8.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
323
+ "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
324
+ "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
326
+ "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
327
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
328
+ "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
329
+ "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
330
+ "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
331
+ "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
332
+ "transformer.h.9.attn.bias": "pytorch_model-00001-of-00003.bin",
333
+ "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
334
+ "transformer.h.9.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
335
+ "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
336
+ "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
337
+ "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
338
+ "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
339
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
340
+ "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
341
+ "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
342
+ "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
343
+ "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
344
+ "transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
345
+ "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
346
+ "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
347
+ }
348
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "errors": "replace",
20
+ "model_max_length": 2048,
21
+ "special_tokens_map_file": null,
22
+ "tokenizer_class": "GPT2Tokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff