Hugging Face's logo

keminglu
/
pivoine-7b

Text Generation
Transformers
PyTorch
bloom
text-generation-inference
Model card Files
xet
Community
1
keminglu commited on
Commit
6304a23
·
1 Parent(s): 16242c4

add checkpoints

Browse files
Files changed (34) hide show
  1. config.json +31 -0
  2. pytorch_model.bin.index.json +372 -0
  3. pytorch_model_00001-of-00032.bin +3 -0
  4. pytorch_model_00002-of-00032.bin +3 -0
  5. pytorch_model_00003-of-00032.bin +3 -0
  6. pytorch_model_00004-of-00032.bin +3 -0
  7. pytorch_model_00005-of-00032.bin +3 -0
  8. pytorch_model_00006-of-00032.bin +3 -0
  9. pytorch_model_00007-of-00032.bin +3 -0
  10. pytorch_model_00008-of-00032.bin +3 -0
  11. pytorch_model_00009-of-00032.bin +3 -0
  12. pytorch_model_00010-of-00032.bin +3 -0
  13. pytorch_model_00011-of-00032.bin +3 -0
  14. pytorch_model_00012-of-00032.bin +3 -0
  15. pytorch_model_00013-of-00032.bin +3 -0
  16. pytorch_model_00014-of-00032.bin +3 -0
  17. pytorch_model_00015-of-00032.bin +3 -0
  18. pytorch_model_00016-of-00032.bin +3 -0
  19. pytorch_model_00017-of-00032.bin +3 -0
  20. pytorch_model_00018-of-00032.bin +3 -0
  21. pytorch_model_00019-of-00032.bin +3 -0
  22. pytorch_model_00020-of-00032.bin +3 -0
  23. pytorch_model_00021-of-00032.bin +3 -0
  24. pytorch_model_00022-of-00032.bin +3 -0
  25. pytorch_model_00023-of-00032.bin +3 -0
  26. pytorch_model_00024-of-00032.bin +3 -0
  27. pytorch_model_00025-of-00032.bin +3 -0
  28. pytorch_model_00026-of-00032.bin +3 -0
  29. pytorch_model_00027-of-00032.bin +3 -0
  30. pytorch_model_00028-of-00032.bin +3 -0
  31. pytorch_model_00029-of-00032.bin +3 -0
  32. pytorch_model_00030-of-00032.bin +3 -0
  33. pytorch_model_00031-of-00032.bin +3 -0
  34. pytorch_model_00032-of-00032.bin +3 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "architectures": [
4
+ "BloomForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_softmax_in_fp32": true,
8
+ "bias_dropout_fusion": true,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "masked_softmax_fusion": true,
16
+ "model_type": "bloom",
17
+ "n_head": 32,
18
+ "n_inner": null,
19
+ "n_layer": 30,
20
+ "offset_alibi": 100,
21
+ "pad_token_id": 3,
22
+ "pretraining_tp": 1,
23
+ "skip_bias_add": true,
24
+ "skip_bias_add_qkv": false,
25
+ "slow_but_exact": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.22.2",
28
+ "unk_token_id": 0,
29
+ "use_cache": true,
30
+ "vocab_size": 250880
31
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14138032128
4
+ },
5
+ "weight_map": {
6
+ "h.0.input_layernorm.bias": "pytorch_model_00002-of-00032.bin",
7
+ "h.0.input_layernorm.weight": "pytorch_model_00002-of-00032.bin",
8
+ "h.0.mlp.dense_4h_to_h.bias": "pytorch_model_00002-of-00032.bin",
9
+ "h.0.mlp.dense_4h_to_h.weight": "pytorch_model_00002-of-00032.bin",
10
+ "h.0.mlp.dense_h_to_4h.bias": "pytorch_model_00002-of-00032.bin",
11
+ "h.0.mlp.dense_h_to_4h.weight": "pytorch_model_00002-of-00032.bin",
12
+ "h.0.post_attention_layernorm.bias": "pytorch_model_00002-of-00032.bin",
13
+ "h.0.post_attention_layernorm.weight": "pytorch_model_00002-of-00032.bin",
14
+ "h.0.self_attention.dense.bias": "pytorch_model_00002-of-00032.bin",
15
+ "h.0.self_attention.dense.weight": "pytorch_model_00002-of-00032.bin",
16
+ "h.0.self_attention.query_key_value.bias": "pytorch_model_00002-of-00032.bin",
17
+ "h.0.self_attention.query_key_value.weight": "pytorch_model_00002-of-00032.bin",
18
+ "h.1.input_layernorm.bias": "pytorch_model_00003-of-00032.bin",
19
+ "h.1.input_layernorm.weight": "pytorch_model_00003-of-00032.bin",
20
+ "h.1.mlp.dense_4h_to_h.bias": "pytorch_model_00003-of-00032.bin",
21
+ "h.1.mlp.dense_4h_to_h.weight": "pytorch_model_00003-of-00032.bin",
22
+ "h.1.mlp.dense_h_to_4h.bias": "pytorch_model_00003-of-00032.bin",
23
+ "h.1.mlp.dense_h_to_4h.weight": "pytorch_model_00003-of-00032.bin",
24
+ "h.1.post_attention_layernorm.bias": "pytorch_model_00003-of-00032.bin",
25
+ "h.1.post_attention_layernorm.weight": "pytorch_model_00003-of-00032.bin",
26
+ "h.1.self_attention.dense.bias": "pytorch_model_00003-of-00032.bin",
27
+ "h.1.self_attention.dense.weight": "pytorch_model_00003-of-00032.bin",
28
+ "h.1.self_attention.query_key_value.bias": "pytorch_model_00003-of-00032.bin",
29
+ "h.1.self_attention.query_key_value.weight": "pytorch_model_00003-of-00032.bin",
30
+ "h.10.input_layernorm.bias": "pytorch_model_00012-of-00032.bin",
31
+ "h.10.input_layernorm.weight": "pytorch_model_00012-of-00032.bin",
32
+ "h.10.mlp.dense_4h_to_h.bias": "pytorch_model_00012-of-00032.bin",
33
+ "h.10.mlp.dense_4h_to_h.weight": "pytorch_model_00012-of-00032.bin",
34
+ "h.10.mlp.dense_h_to_4h.bias": "pytorch_model_00012-of-00032.bin",
35
+ "h.10.mlp.dense_h_to_4h.weight": "pytorch_model_00012-of-00032.bin",
36
+ "h.10.post_attention_layernorm.bias": "pytorch_model_00012-of-00032.bin",
37
+ "h.10.post_attention_layernorm.weight": "pytorch_model_00012-of-00032.bin",
38
+ "h.10.self_attention.dense.bias": "pytorch_model_00012-of-00032.bin",
39
+ "h.10.self_attention.dense.weight": "pytorch_model_00012-of-00032.bin",
40
+ "h.10.self_attention.query_key_value.bias": "pytorch_model_00012-of-00032.bin",
41
+ "h.10.self_attention.query_key_value.weight": "pytorch_model_00012-of-00032.bin",
42
+ "h.11.input_layernorm.bias": "pytorch_model_00013-of-00032.bin",
43
+ "h.11.input_layernorm.weight": "pytorch_model_00013-of-00032.bin",
44
+ "h.11.mlp.dense_4h_to_h.bias": "pytorch_model_00013-of-00032.bin",
45
+ "h.11.mlp.dense_4h_to_h.weight": "pytorch_model_00013-of-00032.bin",
46
+ "h.11.mlp.dense_h_to_4h.bias": "pytorch_model_00013-of-00032.bin",
47
+ "h.11.mlp.dense_h_to_4h.weight": "pytorch_model_00013-of-00032.bin",
48
+ "h.11.post_attention_layernorm.bias": "pytorch_model_00013-of-00032.bin",
49
+ "h.11.post_attention_layernorm.weight": "pytorch_model_00013-of-00032.bin",
50
+ "h.11.self_attention.dense.bias": "pytorch_model_00013-of-00032.bin",
51
+ "h.11.self_attention.dense.weight": "pytorch_model_00013-of-00032.bin",
52
+ "h.11.self_attention.query_key_value.bias": "pytorch_model_00013-of-00032.bin",
53
+ "h.11.self_attention.query_key_value.weight": "pytorch_model_00013-of-00032.bin",
54
+ "h.12.input_layernorm.bias": "pytorch_model_00014-of-00032.bin",
55
+ "h.12.input_layernorm.weight": "pytorch_model_00014-of-00032.bin",
56
+ "h.12.mlp.dense_4h_to_h.bias": "pytorch_model_00014-of-00032.bin",
57
+ "h.12.mlp.dense_4h_to_h.weight": "pytorch_model_00014-of-00032.bin",
58
+ "h.12.mlp.dense_h_to_4h.bias": "pytorch_model_00014-of-00032.bin",
59
+ "h.12.mlp.dense_h_to_4h.weight": "pytorch_model_00014-of-00032.bin",
60
+ "h.12.post_attention_layernorm.bias": "pytorch_model_00014-of-00032.bin",
61
+ "h.12.post_attention_layernorm.weight": "pytorch_model_00014-of-00032.bin",
62
+ "h.12.self_attention.dense.bias": "pytorch_model_00014-of-00032.bin",
63
+ "h.12.self_attention.dense.weight": "pytorch_model_00014-of-00032.bin",
64
+ "h.12.self_attention.query_key_value.bias": "pytorch_model_00014-of-00032.bin",
65
+ "h.12.self_attention.query_key_value.weight": "pytorch_model_00014-of-00032.bin",
66
+ "h.13.input_layernorm.bias": "pytorch_model_00015-of-00032.bin",
67
+ "h.13.input_layernorm.weight": "pytorch_model_00015-of-00032.bin",
68
+ "h.13.mlp.dense_4h_to_h.bias": "pytorch_model_00015-of-00032.bin",
69
+ "h.13.mlp.dense_4h_to_h.weight": "pytorch_model_00015-of-00032.bin",
70
+ "h.13.mlp.dense_h_to_4h.bias": "pytorch_model_00015-of-00032.bin",
71
+ "h.13.mlp.dense_h_to_4h.weight": "pytorch_model_00015-of-00032.bin",
72
+ "h.13.post_attention_layernorm.bias": "pytorch_model_00015-of-00032.bin",
73
+ "h.13.post_attention_layernorm.weight": "pytorch_model_00015-of-00032.bin",
74
+ "h.13.self_attention.dense.bias": "pytorch_model_00015-of-00032.bin",
75
+ "h.13.self_attention.dense.weight": "pytorch_model_00015-of-00032.bin",
76
+ "h.13.self_attention.query_key_value.bias": "pytorch_model_00015-of-00032.bin",
77
+ "h.13.self_attention.query_key_value.weight": "pytorch_model_00015-of-00032.bin",
78
+ "h.14.input_layernorm.bias": "pytorch_model_00016-of-00032.bin",
79
+ "h.14.input_layernorm.weight": "pytorch_model_00016-of-00032.bin",
80
+ "h.14.mlp.dense_4h_to_h.bias": "pytorch_model_00016-of-00032.bin",
81
+ "h.14.mlp.dense_4h_to_h.weight": "pytorch_model_00016-of-00032.bin",
82
+ "h.14.mlp.dense_h_to_4h.bias": "pytorch_model_00016-of-00032.bin",
83
+ "h.14.mlp.dense_h_to_4h.weight": "pytorch_model_00016-of-00032.bin",
84
+ "h.14.post_attention_layernorm.bias": "pytorch_model_00016-of-00032.bin",
85
+ "h.14.post_attention_layernorm.weight": "pytorch_model_00016-of-00032.bin",
86
+ "h.14.self_attention.dense.bias": "pytorch_model_00016-of-00032.bin",
87
+ "h.14.self_attention.dense.weight": "pytorch_model_00016-of-00032.bin",
88
+ "h.14.self_attention.query_key_value.bias": "pytorch_model_00016-of-00032.bin",
89
+ "h.14.self_attention.query_key_value.weight": "pytorch_model_00016-of-00032.bin",
90
+ "h.15.input_layernorm.bias": "pytorch_model_00017-of-00032.bin",
91
+ "h.15.input_layernorm.weight": "pytorch_model_00017-of-00032.bin",
92
+ "h.15.mlp.dense_4h_to_h.bias": "pytorch_model_00017-of-00032.bin",
93
+ "h.15.mlp.dense_4h_to_h.weight": "pytorch_model_00017-of-00032.bin",
94
+ "h.15.mlp.dense_h_to_4h.bias": "pytorch_model_00017-of-00032.bin",
95
+ "h.15.mlp.dense_h_to_4h.weight": "pytorch_model_00017-of-00032.bin",
96
+ "h.15.post_attention_layernorm.bias": "pytorch_model_00017-of-00032.bin",
97
+ "h.15.post_attention_layernorm.weight": "pytorch_model_00017-of-00032.bin",
98
+ "h.15.self_attention.dense.bias": "pytorch_model_00017-of-00032.bin",
99
+ "h.15.self_attention.dense.weight": "pytorch_model_00017-of-00032.bin",
100
+ "h.15.self_attention.query_key_value.bias": "pytorch_model_00017-of-00032.bin",
101
+ "h.15.self_attention.query_key_value.weight": "pytorch_model_00017-of-00032.bin",
102
+ "h.16.input_layernorm.bias": "pytorch_model_00018-of-00032.bin",
103
+ "h.16.input_layernorm.weight": "pytorch_model_00018-of-00032.bin",
104
+ "h.16.mlp.dense_4h_to_h.bias": "pytorch_model_00018-of-00032.bin",
105
+ "h.16.mlp.dense_4h_to_h.weight": "pytorch_model_00018-of-00032.bin",
106
+ "h.16.mlp.dense_h_to_4h.bias": "pytorch_model_00018-of-00032.bin",
107
+ "h.16.mlp.dense_h_to_4h.weight": "pytorch_model_00018-of-00032.bin",
108
+ "h.16.post_attention_layernorm.bias": "pytorch_model_00018-of-00032.bin",
109
+ "h.16.post_attention_layernorm.weight": "pytorch_model_00018-of-00032.bin",
110
+ "h.16.self_attention.dense.bias": "pytorch_model_00018-of-00032.bin",
111
+ "h.16.self_attention.dense.weight": "pytorch_model_00018-of-00032.bin",
112
+ "h.16.self_attention.query_key_value.bias": "pytorch_model_00018-of-00032.bin",
113
+ "h.16.self_attention.query_key_value.weight": "pytorch_model_00018-of-00032.bin",
114
+ "h.17.input_layernorm.bias": "pytorch_model_00019-of-00032.bin",
115
+ "h.17.input_layernorm.weight": "pytorch_model_00019-of-00032.bin",
116
+ "h.17.mlp.dense_4h_to_h.bias": "pytorch_model_00019-of-00032.bin",
117
+ "h.17.mlp.dense_4h_to_h.weight": "pytorch_model_00019-of-00032.bin",
118
+ "h.17.mlp.dense_h_to_4h.bias": "pytorch_model_00019-of-00032.bin",
119
+ "h.17.mlp.dense_h_to_4h.weight": "pytorch_model_00019-of-00032.bin",
120
+ "h.17.post_attention_layernorm.bias": "pytorch_model_00019-of-00032.bin",
121
+ "h.17.post_attention_layernorm.weight": "pytorch_model_00019-of-00032.bin",
122
+ "h.17.self_attention.dense.bias": "pytorch_model_00019-of-00032.bin",
123
+ "h.17.self_attention.dense.weight": "pytorch_model_00019-of-00032.bin",
124
+ "h.17.self_attention.query_key_value.bias": "pytorch_model_00019-of-00032.bin",
125
+ "h.17.self_attention.query_key_value.weight": "pytorch_model_00019-of-00032.bin",
126
+ "h.18.input_layernorm.bias": "pytorch_model_00020-of-00032.bin",
127
+ "h.18.input_layernorm.weight": "pytorch_model_00020-of-00032.bin",
128
+ "h.18.mlp.dense_4h_to_h.bias": "pytorch_model_00020-of-00032.bin",
129
+ "h.18.mlp.dense_4h_to_h.weight": "pytorch_model_00020-of-00032.bin",
130
+ "h.18.mlp.dense_h_to_4h.bias": "pytorch_model_00020-of-00032.bin",
131
+ "h.18.mlp.dense_h_to_4h.weight": "pytorch_model_00020-of-00032.bin",
132
+ "h.18.post_attention_layernorm.bias": "pytorch_model_00020-of-00032.bin",
133
+ "h.18.post_attention_layernorm.weight": "pytorch_model_00020-of-00032.bin",
134
+ "h.18.self_attention.dense.bias": "pytorch_model_00020-of-00032.bin",
135
+ "h.18.self_attention.dense.weight": "pytorch_model_00020-of-00032.bin",
136
+ "h.18.self_attention.query_key_value.bias": "pytorch_model_00020-of-00032.bin",
137
+ "h.18.self_attention.query_key_value.weight": "pytorch_model_00020-of-00032.bin",
138
+ "h.19.input_layernorm.bias": "pytorch_model_00021-of-00032.bin",
139
+ "h.19.input_layernorm.weight": "pytorch_model_00021-of-00032.bin",
140
+ "h.19.mlp.dense_4h_to_h.bias": "pytorch_model_00021-of-00032.bin",
141
+ "h.19.mlp.dense_4h_to_h.weight": "pytorch_model_00021-of-00032.bin",
142
+ "h.19.mlp.dense_h_to_4h.bias": "pytorch_model_00021-of-00032.bin",
143
+ "h.19.mlp.dense_h_to_4h.weight": "pytorch_model_00021-of-00032.bin",
144
+ "h.19.post_attention_layernorm.bias": "pytorch_model_00021-of-00032.bin",
145
+ "h.19.post_attention_layernorm.weight": "pytorch_model_00021-of-00032.bin",
146
+ "h.19.self_attention.dense.bias": "pytorch_model_00021-of-00032.bin",
147
+ "h.19.self_attention.dense.weight": "pytorch_model_00021-of-00032.bin",
148
+ "h.19.self_attention.query_key_value.bias": "pytorch_model_00021-of-00032.bin",
149
+ "h.19.self_attention.query_key_value.weight": "pytorch_model_00021-of-00032.bin",
150
+ "h.2.input_layernorm.bias": "pytorch_model_00004-of-00032.bin",
151
+ "h.2.input_layernorm.weight": "pytorch_model_00004-of-00032.bin",
152
+ "h.2.mlp.dense_4h_to_h.bias": "pytorch_model_00004-of-00032.bin",
153
+ "h.2.mlp.dense_4h_to_h.weight": "pytorch_model_00004-of-00032.bin",
154
+ "h.2.mlp.dense_h_to_4h.bias": "pytorch_model_00004-of-00032.bin",
155
+ "h.2.mlp.dense_h_to_4h.weight": "pytorch_model_00004-of-00032.bin",
156
+ "h.2.post_attention_layernorm.bias": "pytorch_model_00004-of-00032.bin",
157
+ "h.2.post_attention_layernorm.weight": "pytorch_model_00004-of-00032.bin",
158
+ "h.2.self_attention.dense.bias": "pytorch_model_00004-of-00032.bin",
159
+ "h.2.self_attention.dense.weight": "pytorch_model_00004-of-00032.bin",
160
+ "h.2.self_attention.query_key_value.bias": "pytorch_model_00004-of-00032.bin",
161
+ "h.2.self_attention.query_key_value.weight": "pytorch_model_00004-of-00032.bin",
162
+ "h.20.input_layernorm.bias": "pytorch_model_00022-of-00032.bin",
163
+ "h.20.input_layernorm.weight": "pytorch_model_00022-of-00032.bin",
164
+ "h.20.mlp.dense_4h_to_h.bias": "pytorch_model_00022-of-00032.bin",
165
+ "h.20.mlp.dense_4h_to_h.weight": "pytorch_model_00022-of-00032.bin",
166
+ "h.20.mlp.dense_h_to_4h.bias": "pytorch_model_00022-of-00032.bin",
167
+ "h.20.mlp.dense_h_to_4h.weight": "pytorch_model_00022-of-00032.bin",
168
+ "h.20.post_attention_layernorm.bias": "pytorch_model_00022-of-00032.bin",
169
+ "h.20.post_attention_layernorm.weight": "pytorch_model_00022-of-00032.bin",
170
+ "h.20.self_attention.dense.bias": "pytorch_model_00022-of-00032.bin",
171
+ "h.20.self_attention.dense.weight": "pytorch_model_00022-of-00032.bin",
172
+ "h.20.self_attention.query_key_value.bias": "pytorch_model_00022-of-00032.bin",
173
+ "h.20.self_attention.query_key_value.weight": "pytorch_model_00022-of-00032.bin",
174
+ "h.21.input_layernorm.bias": "pytorch_model_00023-of-00032.bin",
175
+ "h.21.input_layernorm.weight": "pytorch_model_00023-of-00032.bin",
176
+ "h.21.mlp.dense_4h_to_h.bias": "pytorch_model_00023-of-00032.bin",
177
+ "h.21.mlp.dense_4h_to_h.weight": "pytorch_model_00023-of-00032.bin",
178
+ "h.21.mlp.dense_h_to_4h.bias": "pytorch_model_00023-of-00032.bin",
179
+ "h.21.mlp.dense_h_to_4h.weight": "pytorch_model_00023-of-00032.bin",
180
+ "h.21.post_attention_layernorm.bias": "pytorch_model_00023-of-00032.bin",
181
+ "h.21.post_attention_layernorm.weight": "pytorch_model_00023-of-00032.bin",
182
+ "h.21.self_attention.dense.bias": "pytorch_model_00023-of-00032.bin",
183
+ "h.21.self_attention.dense.weight": "pytorch_model_00023-of-00032.bin",
184
+ "h.21.self_attention.query_key_value.bias": "pytorch_model_00023-of-00032.bin",
185
+ "h.21.self_attention.query_key_value.weight": "pytorch_model_00023-of-00032.bin",
186
+ "h.22.input_layernorm.bias": "pytorch_model_00024-of-00032.bin",
187
+ "h.22.input_layernorm.weight": "pytorch_model_00024-of-00032.bin",
188
+ "h.22.mlp.dense_4h_to_h.bias": "pytorch_model_00024-of-00032.bin",
189
+ "h.22.mlp.dense_4h_to_h.weight": "pytorch_model_00024-of-00032.bin",
190
+ "h.22.mlp.dense_h_to_4h.bias": "pytorch_model_00024-of-00032.bin",
191
+ "h.22.mlp.dense_h_to_4h.weight": "pytorch_model_00024-of-00032.bin",
192
+ "h.22.post_attention_layernorm.bias": "pytorch_model_00024-of-00032.bin",
193
+ "h.22.post_attention_layernorm.weight": "pytorch_model_00024-of-00032.bin",
194
+ "h.22.self_attention.dense.bias": "pytorch_model_00024-of-00032.bin",
195
+ "h.22.self_attention.dense.weight": "pytorch_model_00024-of-00032.bin",
196
+ "h.22.self_attention.query_key_value.bias": "pytorch_model_00024-of-00032.bin",
197
+ "h.22.self_attention.query_key_value.weight": "pytorch_model_00024-of-00032.bin",
198
+ "h.23.input_layernorm.bias": "pytorch_model_00025-of-00032.bin",
199
+ "h.23.input_layernorm.weight": "pytorch_model_00025-of-00032.bin",
200
+ "h.23.mlp.dense_4h_to_h.bias": "pytorch_model_00025-of-00032.bin",
201
+ "h.23.mlp.dense_4h_to_h.weight": "pytorch_model_00025-of-00032.bin",
202
+ "h.23.mlp.dense_h_to_4h.bias": "pytorch_model_00025-of-00032.bin",
203
+ "h.23.mlp.dense_h_to_4h.weight": "pytorch_model_00025-of-00032.bin",
204
+ "h.23.post_attention_layernorm.bias": "pytorch_model_00025-of-00032.bin",
205
+ "h.23.post_attention_layernorm.weight": "pytorch_model_00025-of-00032.bin",
206
+ "h.23.self_attention.dense.bias": "pytorch_model_00025-of-00032.bin",
207
+ "h.23.self_attention.dense.weight": "pytorch_model_00025-of-00032.bin",
208
+ "h.23.self_attention.query_key_value.bias": "pytorch_model_00025-of-00032.bin",
209
+ "h.23.self_attention.query_key_value.weight": "pytorch_model_00025-of-00032.bin",
210
+ "h.24.input_layernorm.bias": "pytorch_model_00026-of-00032.bin",
211
+ "h.24.input_layernorm.weight": "pytorch_model_00026-of-00032.bin",
212
+ "h.24.mlp.dense_4h_to_h.bias": "pytorch_model_00026-of-00032.bin",
213
+ "h.24.mlp.dense_4h_to_h.weight": "pytorch_model_00026-of-00032.bin",
214
+ "h.24.mlp.dense_h_to_4h.bias": "pytorch_model_00026-of-00032.bin",
215
+ "h.24.mlp.dense_h_to_4h.weight": "pytorch_model_00026-of-00032.bin",
216
+ "h.24.post_attention_layernorm.bias": "pytorch_model_00026-of-00032.bin",
217
+ "h.24.post_attention_layernorm.weight": "pytorch_model_00026-of-00032.bin",
218
+ "h.24.self_attention.dense.bias": "pytorch_model_00026-of-00032.bin",
219
+ "h.24.self_attention.dense.weight": "pytorch_model_00026-of-00032.bin",
220
+ "h.24.self_attention.query_key_value.bias": "pytorch_model_00026-of-00032.bin",
221
+ "h.24.self_attention.query_key_value.weight": "pytorch_model_00026-of-00032.bin",
222
+ "h.25.input_layernorm.bias": "pytorch_model_00027-of-00032.bin",
223
+ "h.25.input_layernorm.weight": "pytorch_model_00027-of-00032.bin",
224
+ "h.25.mlp.dense_4h_to_h.bias": "pytorch_model_00027-of-00032.bin",
225
+ "h.25.mlp.dense_4h_to_h.weight": "pytorch_model_00027-of-00032.bin",
226
+ "h.25.mlp.dense_h_to_4h.bias": "pytorch_model_00027-of-00032.bin",
227
+ "h.25.mlp.dense_h_to_4h.weight": "pytorch_model_00027-of-00032.bin",
228
+ "h.25.post_attention_layernorm.bias": "pytorch_model_00027-of-00032.bin",
229
+ "h.25.post_attention_layernorm.weight": "pytorch_model_00027-of-00032.bin",
230
+ "h.25.self_attention.dense.bias": "pytorch_model_00027-of-00032.bin",
231
+ "h.25.self_attention.dense.weight": "pytorch_model_00027-of-00032.bin",
232
+ "h.25.self_attention.query_key_value.bias": "pytorch_model_00027-of-00032.bin",
233
+ "h.25.self_attention.query_key_value.weight": "pytorch_model_00027-of-00032.bin",
234
+ "h.26.input_layernorm.bias": "pytorch_model_00028-of-00032.bin",
235
+ "h.26.input_layernorm.weight": "pytorch_model_00028-of-00032.bin",
236
+ "h.26.mlp.dense_4h_to_h.bias": "pytorch_model_00028-of-00032.bin",
237
+ "h.26.mlp.dense_4h_to_h.weight": "pytorch_model_00028-of-00032.bin",
238
+ "h.26.mlp.dense_h_to_4h.bias": "pytorch_model_00028-of-00032.bin",
239
+ "h.26.mlp.dense_h_to_4h.weight": "pytorch_model_00028-of-00032.bin",
240
+ "h.26.post_attention_layernorm.bias": "pytorch_model_00028-of-00032.bin",
241
+ "h.26.post_attention_layernorm.weight": "pytorch_model_00028-of-00032.bin",
242
+ "h.26.self_attention.dense.bias": "pytorch_model_00028-of-00032.bin",
243
+ "h.26.self_attention.dense.weight": "pytorch_model_00028-of-00032.bin",
244
+ "h.26.self_attention.query_key_value.bias": "pytorch_model_00028-of-00032.bin",
245
+ "h.26.self_attention.query_key_value.weight": "pytorch_model_00028-of-00032.bin",
246
+ "h.27.input_layernorm.bias": "pytorch_model_00029-of-00032.bin",
247
+ "h.27.input_layernorm.weight": "pytorch_model_00029-of-00032.bin",
248
+ "h.27.mlp.dense_4h_to_h.bias": "pytorch_model_00029-of-00032.bin",
249
+ "h.27.mlp.dense_4h_to_h.weight": "pytorch_model_00029-of-00032.bin",
250
+ "h.27.mlp.dense_h_to_4h.bias": "pytorch_model_00029-of-00032.bin",
251
+ "h.27.mlp.dense_h_to_4h.weight": "pytorch_model_00029-of-00032.bin",
252
+ "h.27.post_attention_layernorm.bias": "pytorch_model_00029-of-00032.bin",
253
+ "h.27.post_attention_layernorm.weight": "pytorch_model_00029-of-00032.bin",
254
+ "h.27.self_attention.dense.bias": "pytorch_model_00029-of-00032.bin",
255
+ "h.27.self_attention.dense.weight": "pytorch_model_00029-of-00032.bin",
256
+ "h.27.self_attention.query_key_value.bias": "pytorch_model_00029-of-00032.bin",
257
+ "h.27.self_attention.query_key_value.weight": "pytorch_model_00029-of-00032.bin",
258
+ "h.28.input_layernorm.bias": "pytorch_model_00030-of-00032.bin",
259
+ "h.28.input_layernorm.weight": "pytorch_model_00030-of-00032.bin",
260
+ "h.28.mlp.dense_4h_to_h.bias": "pytorch_model_00030-of-00032.bin",
261
+ "h.28.mlp.dense_4h_to_h.weight": "pytorch_model_00030-of-00032.bin",
262
+ "h.28.mlp.dense_h_to_4h.bias": "pytorch_model_00030-of-00032.bin",
263
+ "h.28.mlp.dense_h_to_4h.weight": "pytorch_model_00030-of-00032.bin",
264
+ "h.28.post_attention_layernorm.bias": "pytorch_model_00030-of-00032.bin",
265
+ "h.28.post_attention_layernorm.weight": "pytorch_model_00030-of-00032.bin",
266
+ "h.28.self_attention.dense.bias": "pytorch_model_00030-of-00032.bin",
267
+ "h.28.self_attention.dense.weight": "pytorch_model_00030-of-00032.bin",
268
+ "h.28.self_attention.query_key_value.bias": "pytorch_model_00030-of-00032.bin",
269
+ "h.28.self_attention.query_key_value.weight": "pytorch_model_00030-of-00032.bin",
270
+ "h.29.input_layernorm.bias": "pytorch_model_00031-of-00032.bin",
271
+ "h.29.input_layernorm.weight": "pytorch_model_00031-of-00032.bin",
272
+ "h.29.mlp.dense_4h_to_h.bias": "pytorch_model_00031-of-00032.bin",
273
+ "h.29.mlp.dense_4h_to_h.weight": "pytorch_model_00031-of-00032.bin",
274
+ "h.29.mlp.dense_h_to_4h.bias": "pytorch_model_00031-of-00032.bin",
275
+ "h.29.mlp.dense_h_to_4h.weight": "pytorch_model_00031-of-00032.bin",
276
+ "h.29.post_attention_layernorm.bias": "pytorch_model_00031-of-00032.bin",
277
+ "h.29.post_attention_layernorm.weight": "pytorch_model_00031-of-00032.bin",
278
+ "h.29.self_attention.dense.bias": "pytorch_model_00031-of-00032.bin",
279
+ "h.29.self_attention.dense.weight": "pytorch_model_00031-of-00032.bin",
280
+ "h.29.self_attention.query_key_value.bias": "pytorch_model_00031-of-00032.bin",
281
+ "h.29.self_attention.query_key_value.weight": "pytorch_model_00031-of-00032.bin",
282
+ "h.3.input_layernorm.bias": "pytorch_model_00005-of-00032.bin",
283
+ "h.3.input_layernorm.weight": "pytorch_model_00005-of-00032.bin",
284
+ "h.3.mlp.dense_4h_to_h.bias": "pytorch_model_00005-of-00032.bin",
285
+ "h.3.mlp.dense_4h_to_h.weight": "pytorch_model_00005-of-00032.bin",
286
+ "h.3.mlp.dense_h_to_4h.bias": "pytorch_model_00005-of-00032.bin",
287
+ "h.3.mlp.dense_h_to_4h.weight": "pytorch_model_00005-of-00032.bin",
288
+ "h.3.post_attention_layernorm.bias": "pytorch_model_00005-of-00032.bin",
289
+ "h.3.post_attention_layernorm.weight": "pytorch_model_00005-of-00032.bin",
290
+ "h.3.self_attention.dense.bias": "pytorch_model_00005-of-00032.bin",
291
+ "h.3.self_attention.dense.weight": "pytorch_model_00005-of-00032.bin",
292
+ "h.3.self_attention.query_key_value.bias": "pytorch_model_00005-of-00032.bin",
293
+ "h.3.self_attention.query_key_value.weight": "pytorch_model_00005-of-00032.bin",
294
+ "h.4.input_layernorm.bias": "pytorch_model_00006-of-00032.bin",
295
+ "h.4.input_layernorm.weight": "pytorch_model_00006-of-00032.bin",
296
+ "h.4.mlp.dense_4h_to_h.bias": "pytorch_model_00006-of-00032.bin",
297
+ "h.4.mlp.dense_4h_to_h.weight": "pytorch_model_00006-of-00032.bin",
298
+ "h.4.mlp.dense_h_to_4h.bias": "pytorch_model_00006-of-00032.bin",
299
+ "h.4.mlp.dense_h_to_4h.weight": "pytorch_model_00006-of-00032.bin",
300
+ "h.4.post_attention_layernorm.bias": "pytorch_model_00006-of-00032.bin",
301
+ "h.4.post_attention_layernorm.weight": "pytorch_model_00006-of-00032.bin",
302
+ "h.4.self_attention.dense.bias": "pytorch_model_00006-of-00032.bin",
303
+ "h.4.self_attention.dense.weight": "pytorch_model_00006-of-00032.bin",
304
+ "h.4.self_attention.query_key_value.bias": "pytorch_model_00006-of-00032.bin",
305
+ "h.4.self_attention.query_key_value.weight": "pytorch_model_00006-of-00032.bin",
306
+ "h.5.input_layernorm.bias": "pytorch_model_00007-of-00032.bin",
307
+ "h.5.input_layernorm.weight": "pytorch_model_00007-of-00032.bin",
308
+ "h.5.mlp.dense_4h_to_h.bias": "pytorch_model_00007-of-00032.bin",
309
+ "h.5.mlp.dense_4h_to_h.weight": "pytorch_model_00007-of-00032.bin",
310
+ "h.5.mlp.dense_h_to_4h.bias": "pytorch_model_00007-of-00032.bin",
311
+ "h.5.mlp.dense_h_to_4h.weight": "pytorch_model_00007-of-00032.bin",
312
+ "h.5.post_attention_layernorm.bias": "pytorch_model_00007-of-00032.bin",
313
+ "h.5.post_attention_layernorm.weight": "pytorch_model_00007-of-00032.bin",
314
+ "h.5.self_attention.dense.bias": "pytorch_model_00007-of-00032.bin",
315
+ "h.5.self_attention.dense.weight": "pytorch_model_00007-of-00032.bin",
316
+ "h.5.self_attention.query_key_value.bias": "pytorch_model_00007-of-00032.bin",
317
+ "h.5.self_attention.query_key_value.weight": "pytorch_model_00007-of-00032.bin",
318
+ "h.6.input_layernorm.bias": "pytorch_model_00008-of-00032.bin",
319
+ "h.6.input_layernorm.weight": "pytorch_model_00008-of-00032.bin",
320
+ "h.6.mlp.dense_4h_to_h.bias": "pytorch_model_00008-of-00032.bin",
321
+ "h.6.mlp.dense_4h_to_h.weight": "pytorch_model_00008-of-00032.bin",
322
+ "h.6.mlp.dense_h_to_4h.bias": "pytorch_model_00008-of-00032.bin",
323
+ "h.6.mlp.dense_h_to_4h.weight": "pytorch_model_00008-of-00032.bin",
324
+ "h.6.post_attention_layernorm.bias": "pytorch_model_00008-of-00032.bin",
325
+ "h.6.post_attention_layernorm.weight": "pytorch_model_00008-of-00032.bin",
326
+ "h.6.self_attention.dense.bias": "pytorch_model_00008-of-00032.bin",
327
+ "h.6.self_attention.dense.weight": "pytorch_model_00008-of-00032.bin",
328
+ "h.6.self_attention.query_key_value.bias": "pytorch_model_00008-of-00032.bin",
329
+ "h.6.self_attention.query_key_value.weight": "pytorch_model_00008-of-00032.bin",
330
+ "h.7.input_layernorm.bias": "pytorch_model_00009-of-00032.bin",
331
+ "h.7.input_layernorm.weight": "pytorch_model_00009-of-00032.bin",
332
+ "h.7.mlp.dense_4h_to_h.bias": "pytorch_model_00009-of-00032.bin",
333
+ "h.7.mlp.dense_4h_to_h.weight": "pytorch_model_00009-of-00032.bin",
334
+ "h.7.mlp.dense_h_to_4h.bias": "pytorch_model_00009-of-00032.bin",
335
+ "h.7.mlp.dense_h_to_4h.weight": "pytorch_model_00009-of-00032.bin",
336
+ "h.7.post_attention_layernorm.bias": "pytorch_model_00009-of-00032.bin",
337
+ "h.7.post_attention_layernorm.weight": "pytorch_model_00009-of-00032.bin",
338
+ "h.7.self_attention.dense.bias": "pytorch_model_00009-of-00032.bin",
339
+ "h.7.self_attention.dense.weight": "pytorch_model_00009-of-00032.bin",
340
+ "h.7.self_attention.query_key_value.bias": "pytorch_model_00009-of-00032.bin",
341
+ "h.7.self_attention.query_key_value.weight": "pytorch_model_00009-of-00032.bin",
342
+ "h.8.input_layernorm.bias": "pytorch_model_00010-of-00032.bin",
343
+ "h.8.input_layernorm.weight": "pytorch_model_00010-of-00032.bin",
344
+ "h.8.mlp.dense_4h_to_h.bias": "pytorch_model_00010-of-00032.bin",
345
+ "h.8.mlp.dense_4h_to_h.weight": "pytorch_model_00010-of-00032.bin",
346
+ "h.8.mlp.dense_h_to_4h.bias": "pytorch_model_00010-of-00032.bin",
347
+ "h.8.mlp.dense_h_to_4h.weight": "pytorch_model_00010-of-00032.bin",
348
+ "h.8.post_attention_layernorm.bias": "pytorch_model_00010-of-00032.bin",
349
+ "h.8.post_attention_layernorm.weight": "pytorch_model_00010-of-00032.bin",
350
+ "h.8.self_attention.dense.bias": "pytorch_model_00010-of-00032.bin",
351
+ "h.8.self_attention.dense.weight": "pytorch_model_00010-of-00032.bin",
352
+ "h.8.self_attention.query_key_value.bias": "pytorch_model_00010-of-00032.bin",
353
+ "h.8.self_attention.query_key_value.weight": "pytorch_model_00010-of-00032.bin",
354
+ "h.9.input_layernorm.bias": "pytorch_model_00011-of-00032.bin",
355
+ "h.9.input_layernorm.weight": "pytorch_model_00011-of-00032.bin",
356
+ "h.9.mlp.dense_4h_to_h.bias": "pytorch_model_00011-of-00032.bin",
357
+ "h.9.mlp.dense_4h_to_h.weight": "pytorch_model_00011-of-00032.bin",
358
+ "h.9.mlp.dense_h_to_4h.bias": "pytorch_model_00011-of-00032.bin",
359
+ "h.9.mlp.dense_h_to_4h.weight": "pytorch_model_00011-of-00032.bin",
360
+ "h.9.post_attention_layernorm.bias": "pytorch_model_00011-of-00032.bin",
361
+ "h.9.post_attention_layernorm.weight": "pytorch_model_00011-of-00032.bin",
362
+ "h.9.self_attention.dense.bias": "pytorch_model_00011-of-00032.bin",
363
+ "h.9.self_attention.dense.weight": "pytorch_model_00011-of-00032.bin",
364
+ "h.9.self_attention.query_key_value.bias": "pytorch_model_00011-of-00032.bin",
365
+ "h.9.self_attention.query_key_value.weight": "pytorch_model_00011-of-00032.bin",
366
+ "ln_f.bias": "pytorch_model_00032-of-00032.bin",
367
+ "ln_f.weight": "pytorch_model_00032-of-00032.bin",
368
+ "word_embeddings.weight": "pytorch_model_00001-of-00032.bin",
369
+ "word_embeddings_layernorm.bias": "pytorch_model_00001-of-00032.bin",
370
+ "word_embeddings_layernorm.weight": "pytorch_model_00001-of-00032.bin"
371
+ }
372
+ }
pytorch_model_00001-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f970b58c04e9ec212b3f2bed303643de1567caf0aa438526eca2e76ab4d4e3a7
3
+ size 2055226531
pytorch_model_00002-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cfe30d5dd87ce5a6fb15942958198f073602c48aefb691d28179bc9c3905607
3
+ size 402762945
pytorch_model_00003-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf1750fe265a4b389b400000f37f28eb9dd96c377fba1cdd7492c4582ebd4f0
3
+ size 402762945
pytorch_model_00004-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6aea7a4d3c0670463d8ea8158ac80d4dfafa5b18222a94cd5e5378ae80ac5f1
3
+ size 402762945
pytorch_model_00005-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71def96718ec8e604eb956eaac78526b2821b8c5e725b8334f30a35061ab3528
3
+ size 402762945
pytorch_model_00006-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5865d946775b6ccf010860be0050dff28fb84814d6ca9c9292ed2e311fb8c0b2
3
+ size 402762945
pytorch_model_00007-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1469eb3e4d53482770c36ae7f3695658ae968a1f6ba82660af9ee1df561421a6
3
+ size 402762945
pytorch_model_00008-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7855006db4bdf5c4b534fc3eec16d0ff3aa76f00447da96c4732bd2722d4da85
3
+ size 402762945
pytorch_model_00009-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e75e59cddccd3ca8c2de77f1d8159f3580c83e4dc08b27d1d8e583521bef8d8
3
+ size 402762945
pytorch_model_00010-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a84a071e9db3328dbf93176725ed23b019d3dc65cb04199ea639ab29da7e0a96
3
+ size 402762945
pytorch_model_00011-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f27022a9889f286d30eaa23340a5ecbf17bcaf16582d39c3bf2a57f2ed25f8db
3
+ size 402762945
pytorch_model_00012-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f54c4e50dbe619bc4654a33ddb06c7f06323b8d7f703ef9158efce06ead2c5
3
+ size 402762945
pytorch_model_00013-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e1021b26e7b150865f0977f01ee15b8ee616834110b1c62b3f0f489062e2803
3
+ size 402762945
pytorch_model_00014-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbec8738557a758421dd8836c141fd8e531bb440c086a73eeb92410d845a740
3
+ size 402762945
pytorch_model_00015-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3f235224d3a9bda5f0ce3c069fae16945ab43769aeb752c7ec99b623208941
3
+ size 402762945
pytorch_model_00016-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac671f45194f04fdc328216f39b8ab1a484b947dafc26fb73563c634984f18fd
3
+ size 402762945
pytorch_model_00017-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c1101eaa7997cfde08d465dc751efa9ab75b11b2883cd57b5b87c997e2e67c
3
+ size 402762945
pytorch_model_00018-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155286db35668ba1cf439643e9e57ccd1e59baf7b28125ccdd510878e0cbfe49
3
+ size 402762945
pytorch_model_00019-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c36ab7f1427cb4e69359711e494c21fe671a679053274171fd7bf852a8236958
3
+ size 402762945
pytorch_model_00020-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c5bea61cca74eacc265adef20f64106016ca8997112e53fe512d1707a9dfe5
3
+ size 402762945
pytorch_model_00021-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf408de46b99ae7ff93fcf5c71adeeec4c9357477d072ca766bc98b41e5cca3
3
+ size 402762945
pytorch_model_00022-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4123647e8cb94f48e795c2b1364f94c03b49936a77bb2c36aa2c6895578992e5
3
+ size 402762945
pytorch_model_00023-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bea476e2ea832374a1455eb4efdb114fca79dfd4b2240bb7196132375fb02c
3
+ size 402762945
pytorch_model_00024-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05a452eb56bb15e322979493a260a1657572fef5f72d31b87f35439d2748a5e
3
+ size 402762945
pytorch_model_00025-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:922be748a7fa9ea9312bc3bfd4a618c738b6c1289dbadb5da30e648e9a720b40
3
+ size 402762945
pytorch_model_00026-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5236634d00f3604cd69725f619547246dd3a059818f57ac1bb06f41b6ba3e23
3
+ size 402762945
pytorch_model_00027-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f57abd566e0a889430a5b1e4d545a36f06afbfa8c5cbb52926a7eced36b60b
3
+ size 402762945
pytorch_model_00028-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c415db1ffe698b8b3ef1ed7fa0ab9f8c210c39d23a6a256c85253ada02232e
3
+ size 402762945
pytorch_model_00029-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f018704a36d68218629fb24b098d698f95112706943d11adc29eb86d01d5ea63
3
+ size 402762945
pytorch_model_00030-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36821ff047e2037f20d199e08046dbd81fdf326373e46bf91b6dde950125bfa
3
+ size 402762945
pytorch_model_00031-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed374554fa2816b51643f962af8c5b34045f6c9da8e157bfd69e84a370ad2a7
3
+ size 402762945
pytorch_model_00032-of-00032.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b053e6100d106f8519460ec51c8e2d1ecf17362487ca9b79cb90a5f00dc0f276
3
+ size 17319