bryanmildort commited on
Commit
0097d1b
1 Parent(s): c91a9fa

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./gpt_neo_notes",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local",
33
+ "global",
34
+ "local",
35
+ "global",
36
+ "local",
37
+ "global",
38
+ "local",
39
+ "global",
40
+ "local"
41
+ ],
42
+ "attention_types": [
43
+ [
44
+ [
45
+ "global",
46
+ "local"
47
+ ],
48
+ 16
49
+ ]
50
+ ],
51
+ "bos_token_id": 50256,
52
+ "embed_dropout": 0,
53
+ "eos_token_id": 50256,
54
+ "gradient_checkpointing": false,
55
+ "hidden_size": 2560,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": null,
58
+ "layer_norm_epsilon": 1e-05,
59
+ "max_position_embeddings": 2048,
60
+ "model_type": "gpt_neo",
61
+ "num_heads": 20,
62
+ "num_layers": 32,
63
+ "resid_dropout": 0,
64
+ "summary_activation": null,
65
+ "summary_first_dropout": 0.1,
66
+ "summary_proj_to_labels": true,
67
+ "summary_type": "cls_index",
68
+ "summary_use_proj": true,
69
+ "task_specific_params": {
70
+ "text-generation": {
71
+ "do_sample": true,
72
+ "max_length": 50,
73
+ "temperature": 0.9
74
+ }
75
+ },
76
+ "tokenizer_class": "GPT2Tokenizer",
77
+ "torch_dtype": "float32",
78
+ "transformers_version": "4.21.2",
79
+ "use_cache": true,
80
+ "vocab_size": 50258,
81
+ "window_size": 256
82
+ }
dataset_dict.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"splits": ["train"]}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc3aa9f9bfae42a301300058c4f605cd8f421b586147c358c5201046eec086b
3
+ size 9996984169
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96548a9e98d6ff5880959d61f00c0cdb0c8516b2024bce57d01bc7af60e14b6
3
+ size 742638515
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,491 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10739458176
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
7
+ "transformer.h.0.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
8
+ "transformer.h.0.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
9
+ "transformer.h.0.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
10
+ "transformer.h.0.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.1.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.1.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.1.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.1.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.1.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.1.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.1.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.10.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.10.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.10.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.10.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.10.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.10.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.10.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.11.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.11.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.11.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.11.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.11.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.11.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.11.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.12.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.12.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.12.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.12.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.12.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.12.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.12.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.13.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.13.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.13.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.13.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.13.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.13.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.13.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.14.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.14.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.14.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.14.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
100
+ "transformer.h.14.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.14.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.14.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
104
+ "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
105
+ "transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
106
+ "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
107
+ "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
108
+ "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
109
+ "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
110
+ "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "transformer.h.15.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
112
+ "transformer.h.15.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "transformer.h.15.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
114
+ "transformer.h.15.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
115
+ "transformer.h.15.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "transformer.h.15.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
117
+ "transformer.h.15.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
119
+ "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
120
+ "transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
121
+ "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
122
+ "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
123
+ "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
124
+ "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
125
+ "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "transformer.h.16.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
127
+ "transformer.h.16.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "transformer.h.16.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
129
+ "transformer.h.16.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
130
+ "transformer.h.16.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "transformer.h.16.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "transformer.h.16.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
134
+ "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
135
+ "transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
136
+ "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
137
+ "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
138
+ "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
139
+ "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
140
+ "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "transformer.h.17.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
142
+ "transformer.h.17.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "transformer.h.17.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
144
+ "transformer.h.17.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
145
+ "transformer.h.17.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.17.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.17.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
152
+ "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
153
+ "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
154
+ "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
155
+ "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "transformer.h.18.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
157
+ "transformer.h.18.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "transformer.h.18.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
159
+ "transformer.h.18.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
160
+ "transformer.h.18.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "transformer.h.18.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "transformer.h.18.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
164
+ "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
165
+ "transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
166
+ "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
167
+ "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
168
+ "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
169
+ "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
170
+ "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
171
+ "transformer.h.19.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
172
+ "transformer.h.19.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
173
+ "transformer.h.19.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
174
+ "transformer.h.19.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
175
+ "transformer.h.19.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "transformer.h.19.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
177
+ "transformer.h.19.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
179
+ "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
180
+ "transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
181
+ "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
182
+ "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
183
+ "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
184
+ "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
185
+ "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
186
+ "transformer.h.2.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
187
+ "transformer.h.2.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
188
+ "transformer.h.2.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
189
+ "transformer.h.2.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
190
+ "transformer.h.2.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "transformer.h.2.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
192
+ "transformer.h.2.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
194
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
195
+ "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
196
+ "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
197
+ "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
198
+ "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
199
+ "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
200
+ "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
201
+ "transformer.h.20.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
202
+ "transformer.h.20.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "transformer.h.20.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
204
+ "transformer.h.20.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
205
+ "transformer.h.20.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
206
+ "transformer.h.20.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
207
+ "transformer.h.20.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
208
+ "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
209
+ "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
210
+ "transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
211
+ "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
212
+ "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
213
+ "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
214
+ "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
215
+ "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
216
+ "transformer.h.21.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
217
+ "transformer.h.21.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "transformer.h.21.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
219
+ "transformer.h.21.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
220
+ "transformer.h.21.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "transformer.h.21.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "transformer.h.21.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
224
+ "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
225
+ "transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
226
+ "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
227
+ "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
228
+ "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
229
+ "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
230
+ "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "transformer.h.22.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
232
+ "transformer.h.22.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
233
+ "transformer.h.22.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
234
+ "transformer.h.22.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
235
+ "transformer.h.22.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
236
+ "transformer.h.22.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
237
+ "transformer.h.22.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
238
+ "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
239
+ "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
240
+ "transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
241
+ "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
242
+ "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
243
+ "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
244
+ "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
245
+ "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "transformer.h.23.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
247
+ "transformer.h.23.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "transformer.h.23.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
249
+ "transformer.h.23.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
250
+ "transformer.h.23.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "transformer.h.23.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
252
+ "transformer.h.23.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
254
+ "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
255
+ "transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
256
+ "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
257
+ "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
258
+ "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
259
+ "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
260
+ "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
261
+ "transformer.h.24.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
262
+ "transformer.h.24.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "transformer.h.24.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
264
+ "transformer.h.24.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
265
+ "transformer.h.24.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "transformer.h.24.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "transformer.h.24.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
268
+ "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
269
+ "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
270
+ "transformer.h.24.ln_2.bias": "pytorch_model-00001-of-00002.bin",
271
+ "transformer.h.24.ln_2.weight": "pytorch_model-00001-of-00002.bin",
272
+ "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
273
+ "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
274
+ "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
275
+ "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "transformer.h.25.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
277
+ "transformer.h.25.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "transformer.h.25.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
279
+ "transformer.h.25.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
280
+ "transformer.h.25.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "transformer.h.25.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "transformer.h.25.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
283
+ "transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00002.bin",
284
+ "transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00002.bin",
285
+ "transformer.h.25.ln_2.bias": "pytorch_model-00001-of-00002.bin",
286
+ "transformer.h.25.ln_2.weight": "pytorch_model-00001-of-00002.bin",
287
+ "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
288
+ "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
289
+ "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
290
+ "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "transformer.h.26.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
292
+ "transformer.h.26.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "transformer.h.26.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
294
+ "transformer.h.26.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
295
+ "transformer.h.26.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "transformer.h.26.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
297
+ "transformer.h.26.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
298
+ "transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00002.bin",
299
+ "transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00002.bin",
300
+ "transformer.h.26.ln_2.bias": "pytorch_model-00001-of-00002.bin",
301
+ "transformer.h.26.ln_2.weight": "pytorch_model-00001-of-00002.bin",
302
+ "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
303
+ "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
304
+ "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
305
+ "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "transformer.h.27.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
307
+ "transformer.h.27.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
308
+ "transformer.h.27.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
309
+ "transformer.h.27.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
310
+ "transformer.h.27.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "transformer.h.27.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "transformer.h.27.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
313
+ "transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00002.bin",
314
+ "transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00002.bin",
315
+ "transformer.h.27.ln_2.bias": "pytorch_model-00001-of-00002.bin",
316
+ "transformer.h.27.ln_2.weight": "pytorch_model-00001-of-00002.bin",
317
+ "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
318
+ "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
319
+ "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
320
+ "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "transformer.h.28.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
322
+ "transformer.h.28.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
323
+ "transformer.h.28.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
324
+ "transformer.h.28.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
325
+ "transformer.h.28.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "transformer.h.28.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
327
+ "transformer.h.28.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "transformer.h.28.ln_1.bias": "pytorch_model-00001-of-00002.bin",
329
+ "transformer.h.28.ln_1.weight": "pytorch_model-00001-of-00002.bin",
330
+ "transformer.h.28.ln_2.bias": "pytorch_model-00001-of-00002.bin",
331
+ "transformer.h.28.ln_2.weight": "pytorch_model-00001-of-00002.bin",
332
+ "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
333
+ "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
334
+ "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
335
+ "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
336
+ "transformer.h.29.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
337
+ "transformer.h.29.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
338
+ "transformer.h.29.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
339
+ "transformer.h.29.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
340
+ "transformer.h.29.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
341
+ "transformer.h.29.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
342
+ "transformer.h.29.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "transformer.h.29.ln_1.bias": "pytorch_model-00001-of-00002.bin",
344
+ "transformer.h.29.ln_1.weight": "pytorch_model-00001-of-00002.bin",
345
+ "transformer.h.29.ln_2.bias": "pytorch_model-00001-of-00002.bin",
346
+ "transformer.h.29.ln_2.weight": "pytorch_model-00001-of-00002.bin",
347
+ "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
348
+ "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
349
+ "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
350
+ "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
351
+ "transformer.h.3.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
352
+ "transformer.h.3.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
353
+ "transformer.h.3.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
354
+ "transformer.h.3.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
355
+ "transformer.h.3.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
356
+ "transformer.h.3.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
357
+ "transformer.h.3.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
358
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
359
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
360
+ "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
361
+ "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
362
+ "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
363
+ "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
364
+ "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
365
+ "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
366
+ "transformer.h.30.attn.attention.bias": "pytorch_model-00002-of-00002.bin",
367
+ "transformer.h.30.attn.attention.k_proj.weight": "pytorch_model-00002-of-00002.bin",
368
+ "transformer.h.30.attn.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
369
+ "transformer.h.30.attn.attention.out_proj.bias": "pytorch_model-00002-of-00002.bin",
370
+ "transformer.h.30.attn.attention.out_proj.weight": "pytorch_model-00002-of-00002.bin",
371
+ "transformer.h.30.attn.attention.q_proj.weight": "pytorch_model-00002-of-00002.bin",
372
+ "transformer.h.30.attn.attention.v_proj.weight": "pytorch_model-00002-of-00002.bin",
373
+ "transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
374
+ "transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
375
+ "transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
376
+ "transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
377
+ "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
378
+ "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
379
+ "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
380
+ "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
381
+ "transformer.h.31.attn.attention.bias": "pytorch_model-00002-of-00002.bin",
382
+ "transformer.h.31.attn.attention.k_proj.weight": "pytorch_model-00002-of-00002.bin",
383
+ "transformer.h.31.attn.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
384
+ "transformer.h.31.attn.attention.out_proj.bias": "pytorch_model-00002-of-00002.bin",
385
+ "transformer.h.31.attn.attention.out_proj.weight": "pytorch_model-00002-of-00002.bin",
386
+ "transformer.h.31.attn.attention.q_proj.weight": "pytorch_model-00002-of-00002.bin",
387
+ "transformer.h.31.attn.attention.v_proj.weight": "pytorch_model-00002-of-00002.bin",
388
+ "transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
389
+ "transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
390
+ "transformer.h.31.ln_2.bias": "pytorch_model-00002-of-00002.bin",
391
+ "transformer.h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
392
+ "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
393
+ "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
394
+ "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
395
+ "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
396
+ "transformer.h.4.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
397
+ "transformer.h.4.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
398
+ "transformer.h.4.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
399
+ "transformer.h.4.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
400
+ "transformer.h.4.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
401
+ "transformer.h.4.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
402
+ "transformer.h.4.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
403
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
404
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
405
+ "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
406
+ "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
407
+ "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
408
+ "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
409
+ "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
410
+ "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
411
+ "transformer.h.5.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
412
+ "transformer.h.5.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
413
+ "transformer.h.5.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
414
+ "transformer.h.5.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
415
+ "transformer.h.5.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
416
+ "transformer.h.5.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
417
+ "transformer.h.5.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
418
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
419
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
420
+ "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
421
+ "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
422
+ "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
423
+ "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
424
+ "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
425
+ "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
426
+ "transformer.h.6.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
427
+ "transformer.h.6.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
428
+ "transformer.h.6.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
429
+ "transformer.h.6.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
430
+ "transformer.h.6.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
431
+ "transformer.h.6.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
432
+ "transformer.h.6.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
433
+ "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
434
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
435
+ "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
436
+ "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
437
+ "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
438
+ "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
439
+ "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
440
+ "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
441
+ "transformer.h.7.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
442
+ "transformer.h.7.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
443
+ "transformer.h.7.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
444
+ "transformer.h.7.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
445
+ "transformer.h.7.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
446
+ "transformer.h.7.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
447
+ "transformer.h.7.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
448
+ "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
449
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
450
+ "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
451
+ "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
452
+ "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
453
+ "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
454
+ "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
455
+ "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
456
+ "transformer.h.8.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
457
+ "transformer.h.8.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
458
+ "transformer.h.8.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
459
+ "transformer.h.8.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
460
+ "transformer.h.8.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
461
+ "transformer.h.8.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
462
+ "transformer.h.8.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
463
+ "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
464
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
465
+ "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
466
+ "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
467
+ "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
468
+ "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
469
+ "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
470
+ "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
471
+ "transformer.h.9.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
472
+ "transformer.h.9.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
473
+ "transformer.h.9.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
474
+ "transformer.h.9.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
475
+ "transformer.h.9.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
476
+ "transformer.h.9.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
477
+ "transformer.h.9.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
478
+ "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
479
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
480
+ "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
481
+ "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
482
+ "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
483
+ "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
484
+ "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
485
+ "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
486
+ "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
487
+ "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
488
+ "transformer.wpe.weight": "pytorch_model-00001-of-00002.bin",
489
+ "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
490
+ }
491
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ea18950096058bc7a3f42f4cf3d20049b6403c8e913ecd41f1c4c4a8c4de2b
3
+ size 3323
vocab.json ADDED
The diff for this file is too large to render. See raw diff