BigBri commited on
Commit
55aefff
1 Parent(s): 4a255f6

Upload model

Browse files
config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "4481e2dd073f8ac9f8351b6cc0c5958e911f96f9",
3
+ "_name_or_path": "Salesforce/codet5p-16b",
4
+ "architectures": [
5
+ "CodeT5pEncoderDecoderModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "Salesforce/codet5p-16b--configuration_codet5p.CodeT5pConfig",
9
+ "AutoModel": "Salesforce/codet5p-16b--modeling_codet5p.CodeGenModel",
10
+ "AutoModelForSeq2SeqLM": "Salesforce/codet5p-16b--modeling_codet5p.CodeT5pEncoderDecoderModel"
11
+ },
12
+ "decoder": {
13
+ "_name_or_path": "codet5p-16b-decoder",
14
+ "activation_function": "gelu_new",
15
+ "add_cross_attention": true,
16
+ "architectures": [
17
+ "CodeT5pForCausalLM"
18
+ ],
19
+ "attn_pdrop": 0.0,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": 1,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "embd_pdrop": 0.0,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 50256,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "gradient_checkpointing": false,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "is_decoder": true,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1
47
+ },
48
+ "layer_norm_epsilon": 1e-05,
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "min_length": 0,
52
+ "model_type": "codet5p_module",
53
+ "n_ctx": 2048,
54
+ "n_embd": 6144,
55
+ "n_head": 24,
56
+ "n_inner": null,
57
+ "n_layer": 34,
58
+ "n_positions": 2048,
59
+ "no_repeat_ngram_size": 0,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": null,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "resid_pdrop": 0.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "rotary_dim": 64,
76
+ "scale_attn_weights": true,
77
+ "sep_token_id": null,
78
+ "summary_activation": null,
79
+ "summary_first_dropout": 0.1,
80
+ "summary_proj_to_labels": true,
81
+ "summary_type": "cls_index",
82
+ "summary_use_proj": true,
83
+ "suppress_tokens": null,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": false,
89
+ "tokenizer_class": "GPT2Tokenizer",
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": "float16",
93
+ "torchscript": false,
94
+ "transformers_version": "4.30.2",
95
+ "typical_p": 1.0,
96
+ "use_bfloat16": false,
97
+ "use_cache": true,
98
+ "vocab_size": 51200
99
+ },
100
+ "encoder": {
101
+ "_name_or_path": "codet5p-350m-encoder",
102
+ "activation_function": "gelu_new",
103
+ "add_cross_attention": false,
104
+ "architectures": [
105
+ "CodeT5pModel"
106
+ ],
107
+ "attn_pdrop": 0.0,
108
+ "bad_words_ids": null,
109
+ "begin_suppress_tokens": null,
110
+ "bos_token_id": 1,
111
+ "chunk_size_feed_forward": 0,
112
+ "cross_attention_hidden_size": null,
113
+ "decoder_start_token_id": null,
114
+ "diversity_penalty": 0.0,
115
+ "do_sample": false,
116
+ "early_stopping": false,
117
+ "embd_pdrop": 0.0,
118
+ "encoder_no_repeat_ngram_size": 0,
119
+ "eos_token_id": 50256,
120
+ "exponential_decay_length_penalty": null,
121
+ "finetuning_task": null,
122
+ "forced_bos_token_id": null,
123
+ "forced_eos_token_id": null,
124
+ "gradient_checkpointing": false,
125
+ "id2label": {
126
+ "0": "LABEL_0",
127
+ "1": "LABEL_1"
128
+ },
129
+ "initializer_range": 0.02,
130
+ "is_decoder": false,
131
+ "is_encoder_decoder": false,
132
+ "label2id": {
133
+ "LABEL_0": 0,
134
+ "LABEL_1": 1
135
+ },
136
+ "layer_norm_epsilon": 1e-05,
137
+ "length_penalty": 1.0,
138
+ "max_length": 20,
139
+ "min_length": 0,
140
+ "model_type": "codet5p_module",
141
+ "n_ctx": 2048,
142
+ "n_embd": 1024,
143
+ "n_head": 16,
144
+ "n_inner": null,
145
+ "n_layer": 20,
146
+ "n_positions": 2048,
147
+ "no_repeat_ngram_size": 0,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_return_sequences": 1,
151
+ "output_attentions": false,
152
+ "output_hidden_states": false,
153
+ "output_scores": false,
154
+ "pad_token_id": null,
155
+ "prefix": null,
156
+ "problem_type": null,
157
+ "pruned_heads": {},
158
+ "remove_invalid_values": false,
159
+ "repetition_penalty": 1.0,
160
+ "resid_pdrop": 0.0,
161
+ "return_dict": true,
162
+ "return_dict_in_generate": false,
163
+ "rotary_dim": 32,
164
+ "scale_attn_weights": true,
165
+ "sep_token_id": null,
166
+ "summary_activation": null,
167
+ "summary_first_dropout": 0.1,
168
+ "summary_proj_to_labels": true,
169
+ "summary_type": "cls_index",
170
+ "summary_use_proj": true,
171
+ "suppress_tokens": null,
172
+ "task_specific_params": null,
173
+ "temperature": 1.0,
174
+ "tf_legacy_loss": false,
175
+ "tie_encoder_decoder": false,
176
+ "tie_word_embeddings": false,
177
+ "tokenizer_class": "GPT2Tokenizer",
178
+ "top_k": 50,
179
+ "top_p": 1.0,
180
+ "torch_dtype": "float16",
181
+ "torchscript": false,
182
+ "transformers_version": "4.30.2",
183
+ "typical_p": 1.0,
184
+ "use_bfloat16": false,
185
+ "use_cache": true,
186
+ "vocab_size": 51200
187
+ },
188
+ "is_encoder_decoder": true,
189
+ "model_type": "codet5p",
190
+ "torch_dtype": "float16",
191
+ "transformers_version": null
192
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.30.2"
6
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520e90e405dc2ed8717fd25b68ab8010b5903cca15c2eeb18a292c2d88e87bf5
3
+ size 10742862340
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ad7d34a7744f2538f02e0a3429b888b83885e975b06748ca5434f3684e60ec
3
+ size 9706562615
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:213a143a072890979bb8baebdb0e433920d113f5bc359cb43fc24ac428bb0d2b
3
+ size 9710745549
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03cfaa7cbfbda8bfd793d9ba8b816889a7b6cb9a8f959b6b405e12f7b0151a53
3
+ size 3058017461
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,507 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 32399855616
4
+ },
5
+ "weight_map": {
6
+ "decoder.lm_head.bias": "pytorch_model-00004-of-00004.bin",
7
+ "decoder.lm_head.weight": "pytorch_model-00004-of-00004.bin",
8
+ "decoder.transformer.h.0.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
9
+ "decoder.transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "decoder.transformer.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "decoder.transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00004.bin",
12
+ "decoder.transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00004.bin",
13
+ "decoder.transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
14
+ "decoder.transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
15
+ "decoder.transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
16
+ "decoder.transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
17
+ "decoder.transformer.h.1.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
18
+ "decoder.transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "decoder.transformer.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "decoder.transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00004.bin",
21
+ "decoder.transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00004.bin",
22
+ "decoder.transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
23
+ "decoder.transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
24
+ "decoder.transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
25
+ "decoder.transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
26
+ "decoder.transformer.h.10.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
27
+ "decoder.transformer.h.10.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
28
+ "decoder.transformer.h.10.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
29
+ "decoder.transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00004.bin",
30
+ "decoder.transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00004.bin",
31
+ "decoder.transformer.h.10.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
32
+ "decoder.transformer.h.10.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
33
+ "decoder.transformer.h.10.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
34
+ "decoder.transformer.h.10.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
35
+ "decoder.transformer.h.11.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
36
+ "decoder.transformer.h.11.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "decoder.transformer.h.11.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "decoder.transformer.h.11.ln_1.bias": "pytorch_model-00002-of-00004.bin",
39
+ "decoder.transformer.h.11.ln_1.weight": "pytorch_model-00002-of-00004.bin",
40
+ "decoder.transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
41
+ "decoder.transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
42
+ "decoder.transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
43
+ "decoder.transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
44
+ "decoder.transformer.h.12.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
45
+ "decoder.transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "decoder.transformer.h.12.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
47
+ "decoder.transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00004.bin",
48
+ "decoder.transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00004.bin",
49
+ "decoder.transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
50
+ "decoder.transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
51
+ "decoder.transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
52
+ "decoder.transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
53
+ "decoder.transformer.h.13.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
54
+ "decoder.transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "decoder.transformer.h.13.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "decoder.transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00004.bin",
57
+ "decoder.transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00004.bin",
58
+ "decoder.transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
59
+ "decoder.transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
60
+ "decoder.transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
61
+ "decoder.transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
62
+ "decoder.transformer.h.14.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
63
+ "decoder.transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "decoder.transformer.h.14.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "decoder.transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00004.bin",
66
+ "decoder.transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00004.bin",
67
+ "decoder.transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
68
+ "decoder.transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
69
+ "decoder.transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
70
+ "decoder.transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
71
+ "decoder.transformer.h.15.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
72
+ "decoder.transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
73
+ "decoder.transformer.h.15.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
74
+ "decoder.transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00004.bin",
75
+ "decoder.transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00004.bin",
76
+ "decoder.transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
77
+ "decoder.transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
78
+ "decoder.transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
79
+ "decoder.transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
80
+ "decoder.transformer.h.16.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
81
+ "decoder.transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "decoder.transformer.h.16.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "decoder.transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00004.bin",
84
+ "decoder.transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00004.bin",
85
+ "decoder.transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
86
+ "decoder.transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
87
+ "decoder.transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
88
+ "decoder.transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
89
+ "decoder.transformer.h.17.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
90
+ "decoder.transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "decoder.transformer.h.17.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "decoder.transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00004.bin",
93
+ "decoder.transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00004.bin",
94
+ "decoder.transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
95
+ "decoder.transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
96
+ "decoder.transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
97
+ "decoder.transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
98
+ "decoder.transformer.h.18.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
99
+ "decoder.transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
100
+ "decoder.transformer.h.18.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
101
+ "decoder.transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00004.bin",
102
+ "decoder.transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00004.bin",
103
+ "decoder.transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
104
+ "decoder.transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
105
+ "decoder.transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
106
+ "decoder.transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
107
+ "decoder.transformer.h.19.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
108
+ "decoder.transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
109
+ "decoder.transformer.h.19.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
110
+ "decoder.transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00004.bin",
111
+ "decoder.transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00004.bin",
112
+ "decoder.transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
113
+ "decoder.transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
114
+ "decoder.transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00004.bin",
115
+ "decoder.transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00004.bin",
116
+ "decoder.transformer.h.2.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
117
+ "decoder.transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
118
+ "decoder.transformer.h.2.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
119
+ "decoder.transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00004.bin",
120
+ "decoder.transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00004.bin",
121
+ "decoder.transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
122
+ "decoder.transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
123
+ "decoder.transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
124
+ "decoder.transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
125
+ "decoder.transformer.h.20.attn.causal_mask": "pytorch_model-00002-of-00004.bin",
126
+ "decoder.transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
127
+ "decoder.transformer.h.20.attn.qkv_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "decoder.transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00004.bin",
129
+ "decoder.transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00004.bin",
130
+ "decoder.transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00004.bin",
131
+ "decoder.transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00004.bin",
132
+ "decoder.transformer.h.20.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
133
+ "decoder.transformer.h.20.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
134
+ "decoder.transformer.h.21.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
135
+ "decoder.transformer.h.21.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
136
+ "decoder.transformer.h.21.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
137
+ "decoder.transformer.h.21.ln_1.bias": "pytorch_model-00003-of-00004.bin",
138
+ "decoder.transformer.h.21.ln_1.weight": "pytorch_model-00003-of-00004.bin",
139
+ "decoder.transformer.h.21.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
140
+ "decoder.transformer.h.21.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
141
+ "decoder.transformer.h.21.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
142
+ "decoder.transformer.h.21.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
143
+ "decoder.transformer.h.22.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
144
+ "decoder.transformer.h.22.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
145
+ "decoder.transformer.h.22.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
146
+ "decoder.transformer.h.22.ln_1.bias": "pytorch_model-00003-of-00004.bin",
147
+ "decoder.transformer.h.22.ln_1.weight": "pytorch_model-00003-of-00004.bin",
148
+ "decoder.transformer.h.22.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
149
+ "decoder.transformer.h.22.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
150
+ "decoder.transformer.h.22.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
151
+ "decoder.transformer.h.22.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
152
+ "decoder.transformer.h.23.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
153
+ "decoder.transformer.h.23.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "decoder.transformer.h.23.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
155
+ "decoder.transformer.h.23.ln_1.bias": "pytorch_model-00003-of-00004.bin",
156
+ "decoder.transformer.h.23.ln_1.weight": "pytorch_model-00003-of-00004.bin",
157
+ "decoder.transformer.h.23.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
158
+ "decoder.transformer.h.23.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
159
+ "decoder.transformer.h.23.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
160
+ "decoder.transformer.h.23.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
161
+ "decoder.transformer.h.24.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
162
+ "decoder.transformer.h.24.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
163
+ "decoder.transformer.h.24.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
164
+ "decoder.transformer.h.24.ln_1.bias": "pytorch_model-00003-of-00004.bin",
165
+ "decoder.transformer.h.24.ln_1.weight": "pytorch_model-00003-of-00004.bin",
166
+ "decoder.transformer.h.24.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
167
+ "decoder.transformer.h.24.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
168
+ "decoder.transformer.h.24.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
169
+ "decoder.transformer.h.24.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
170
+ "decoder.transformer.h.25.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
171
+ "decoder.transformer.h.25.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "decoder.transformer.h.25.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "decoder.transformer.h.25.ln_1.bias": "pytorch_model-00003-of-00004.bin",
174
+ "decoder.transformer.h.25.ln_1.weight": "pytorch_model-00003-of-00004.bin",
175
+ "decoder.transformer.h.25.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
176
+ "decoder.transformer.h.25.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
177
+ "decoder.transformer.h.25.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
178
+ "decoder.transformer.h.25.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
179
+ "decoder.transformer.h.26.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
180
+ "decoder.transformer.h.26.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "decoder.transformer.h.26.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
182
+ "decoder.transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00004.bin",
183
+ "decoder.transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00004.bin",
184
+ "decoder.transformer.h.26.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
185
+ "decoder.transformer.h.26.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
186
+ "decoder.transformer.h.26.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
187
+ "decoder.transformer.h.26.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
188
+ "decoder.transformer.h.27.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
189
+ "decoder.transformer.h.27.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "decoder.transformer.h.27.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "decoder.transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00004.bin",
192
+ "decoder.transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00004.bin",
193
+ "decoder.transformer.h.27.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
194
+ "decoder.transformer.h.27.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
195
+ "decoder.transformer.h.27.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
196
+ "decoder.transformer.h.27.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
197
+ "decoder.transformer.h.28.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
198
+ "decoder.transformer.h.28.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
199
+ "decoder.transformer.h.28.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "decoder.transformer.h.28.ln_1.bias": "pytorch_model-00003-of-00004.bin",
201
+ "decoder.transformer.h.28.ln_1.weight": "pytorch_model-00003-of-00004.bin",
202
+ "decoder.transformer.h.28.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
203
+ "decoder.transformer.h.28.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
204
+ "decoder.transformer.h.28.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
205
+ "decoder.transformer.h.28.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
206
+ "decoder.transformer.h.29.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
207
+ "decoder.transformer.h.29.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "decoder.transformer.h.29.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
209
+ "decoder.transformer.h.29.ln_1.bias": "pytorch_model-00003-of-00004.bin",
210
+ "decoder.transformer.h.29.ln_1.weight": "pytorch_model-00003-of-00004.bin",
211
+ "decoder.transformer.h.29.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
212
+ "decoder.transformer.h.29.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
213
+ "decoder.transformer.h.29.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
214
+ "decoder.transformer.h.29.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
215
+ "decoder.transformer.h.3.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
216
+ "decoder.transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
217
+ "decoder.transformer.h.3.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
218
+ "decoder.transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00004.bin",
219
+ "decoder.transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00004.bin",
220
+ "decoder.transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
221
+ "decoder.transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
222
+ "decoder.transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
223
+ "decoder.transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
224
+ "decoder.transformer.h.30.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
225
+ "decoder.transformer.h.30.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "decoder.transformer.h.30.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "decoder.transformer.h.30.ln_1.bias": "pytorch_model-00003-of-00004.bin",
228
+ "decoder.transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00004.bin",
229
+ "decoder.transformer.h.30.mlp.fc_in.bias": "pytorch_model-00003-of-00004.bin",
230
+ "decoder.transformer.h.30.mlp.fc_in.weight": "pytorch_model-00003-of-00004.bin",
231
+ "decoder.transformer.h.30.mlp.fc_out.bias": "pytorch_model-00003-of-00004.bin",
232
+ "decoder.transformer.h.30.mlp.fc_out.weight": "pytorch_model-00003-of-00004.bin",
233
+ "decoder.transformer.h.31.attn.causal_mask": "pytorch_model-00003-of-00004.bin",
234
+ "decoder.transformer.h.31.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
235
+ "decoder.transformer.h.31.attn.qkv_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "decoder.transformer.h.31.ln_1.bias": "pytorch_model-00003-of-00004.bin",
237
+ "decoder.transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00004.bin",
238
+ "decoder.transformer.h.31.mlp.fc_in.bias": "pytorch_model-00004-of-00004.bin",
239
+ "decoder.transformer.h.31.mlp.fc_in.weight": "pytorch_model-00004-of-00004.bin",
240
+ "decoder.transformer.h.31.mlp.fc_out.bias": "pytorch_model-00004-of-00004.bin",
241
+ "decoder.transformer.h.31.mlp.fc_out.weight": "pytorch_model-00004-of-00004.bin",
242
+ "decoder.transformer.h.32.attn.causal_mask": "pytorch_model-00004-of-00004.bin",
243
+ "decoder.transformer.h.32.attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
244
+ "decoder.transformer.h.32.attn.qkv_proj.weight": "pytorch_model-00004-of-00004.bin",
245
+ "decoder.transformer.h.32.ln_1.bias": "pytorch_model-00004-of-00004.bin",
246
+ "decoder.transformer.h.32.ln_1.weight": "pytorch_model-00004-of-00004.bin",
247
+ "decoder.transformer.h.32.mlp.fc_in.bias": "pytorch_model-00004-of-00004.bin",
248
+ "decoder.transformer.h.32.mlp.fc_in.weight": "pytorch_model-00004-of-00004.bin",
249
+ "decoder.transformer.h.32.mlp.fc_out.bias": "pytorch_model-00004-of-00004.bin",
250
+ "decoder.transformer.h.32.mlp.fc_out.weight": "pytorch_model-00004-of-00004.bin",
251
+ "decoder.transformer.h.33.attn.causal_mask": "pytorch_model-00004-of-00004.bin",
252
+ "decoder.transformer.h.33.attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
253
+ "decoder.transformer.h.33.attn.qkv_proj.weight": "pytorch_model-00004-of-00004.bin",
254
+ "decoder.transformer.h.33.crossattention.causal_mask": "pytorch_model-00004-of-00004.bin",
255
+ "decoder.transformer.h.33.crossattention.out_proj.weight": "pytorch_model-00001-of-00004.bin",
256
+ "decoder.transformer.h.33.crossattention.q_attn.weight": "pytorch_model-00001-of-00004.bin",
257
+ "decoder.transformer.h.33.crossattention.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
258
+ "decoder.transformer.h.33.ln_1.bias": "pytorch_model-00004-of-00004.bin",
259
+ "decoder.transformer.h.33.ln_1.weight": "pytorch_model-00004-of-00004.bin",
260
+ "decoder.transformer.h.33.mlp.fc_in.bias": "pytorch_model-00004-of-00004.bin",
261
+ "decoder.transformer.h.33.mlp.fc_in.weight": "pytorch_model-00004-of-00004.bin",
262
+ "decoder.transformer.h.33.mlp.fc_out.bias": "pytorch_model-00004-of-00004.bin",
263
+ "decoder.transformer.h.33.mlp.fc_out.weight": "pytorch_model-00004-of-00004.bin",
264
+ "decoder.transformer.h.4.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
265
+ "decoder.transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
266
+ "decoder.transformer.h.4.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
267
+ "decoder.transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00004.bin",
268
+ "decoder.transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00004.bin",
269
+ "decoder.transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
270
+ "decoder.transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
271
+ "decoder.transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
272
+ "decoder.transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
273
+ "decoder.transformer.h.5.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
274
+ "decoder.transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
275
+ "decoder.transformer.h.5.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "decoder.transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00004.bin",
277
+ "decoder.transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00004.bin",
278
+ "decoder.transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
279
+ "decoder.transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
280
+ "decoder.transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
281
+ "decoder.transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
282
+ "decoder.transformer.h.6.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
283
+ "decoder.transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
284
+ "decoder.transformer.h.6.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
285
+ "decoder.transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00004.bin",
286
+ "decoder.transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00004.bin",
287
+ "decoder.transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
288
+ "decoder.transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
289
+ "decoder.transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
290
+ "decoder.transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
291
+ "decoder.transformer.h.7.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
292
+ "decoder.transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
293
+ "decoder.transformer.h.7.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
294
+ "decoder.transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00004.bin",
295
+ "decoder.transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00004.bin",
296
+ "decoder.transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
297
+ "decoder.transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
298
+ "decoder.transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
299
+ "decoder.transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
300
+ "decoder.transformer.h.8.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
301
+ "decoder.transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
302
+ "decoder.transformer.h.8.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
303
+ "decoder.transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00004.bin",
304
+ "decoder.transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00004.bin",
305
+ "decoder.transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
306
+ "decoder.transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
307
+ "decoder.transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
308
+ "decoder.transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
309
+ "decoder.transformer.h.9.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
310
+ "decoder.transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
311
+ "decoder.transformer.h.9.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
312
+ "decoder.transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00004.bin",
313
+ "decoder.transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00004.bin",
314
+ "decoder.transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
315
+ "decoder.transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
316
+ "decoder.transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
317
+ "decoder.transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
318
+ "decoder.transformer.ln_f.bias": "pytorch_model-00004-of-00004.bin",
319
+ "decoder.transformer.ln_f.weight": "pytorch_model-00004-of-00004.bin",
320
+ "decoder.transformer.wte.weight": "pytorch_model-00001-of-00004.bin",
321
+ "enc_to_dec_proj.bias": "pytorch_model-00001-of-00004.bin",
322
+ "enc_to_dec_proj.weight": "pytorch_model-00001-of-00004.bin",
323
+ "encoder.h.0.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
324
+ "encoder.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
325
+ "encoder.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
326
+ "encoder.h.0.ln_1.bias": "pytorch_model-00001-of-00004.bin",
327
+ "encoder.h.0.ln_1.weight": "pytorch_model-00001-of-00004.bin",
328
+ "encoder.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
329
+ "encoder.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
330
+ "encoder.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
331
+ "encoder.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
332
+ "encoder.h.1.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
333
+ "encoder.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
334
+ "encoder.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
335
+ "encoder.h.1.ln_1.bias": "pytorch_model-00001-of-00004.bin",
336
+ "encoder.h.1.ln_1.weight": "pytorch_model-00001-of-00004.bin",
337
+ "encoder.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
338
+ "encoder.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
339
+ "encoder.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
340
+ "encoder.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
341
+ "encoder.h.10.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
342
+ "encoder.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
343
+ "encoder.h.10.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
344
+ "encoder.h.10.ln_1.bias": "pytorch_model-00001-of-00004.bin",
345
+ "encoder.h.10.ln_1.weight": "pytorch_model-00001-of-00004.bin",
346
+ "encoder.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
347
+ "encoder.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
348
+ "encoder.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
349
+ "encoder.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
350
+ "encoder.h.11.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
351
+ "encoder.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
352
+ "encoder.h.11.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
353
+ "encoder.h.11.ln_1.bias": "pytorch_model-00001-of-00004.bin",
354
+ "encoder.h.11.ln_1.weight": "pytorch_model-00001-of-00004.bin",
355
+ "encoder.h.11.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
356
+ "encoder.h.11.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
357
+ "encoder.h.11.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
358
+ "encoder.h.11.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
359
+ "encoder.h.12.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
360
+ "encoder.h.12.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
361
+ "encoder.h.12.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
362
+ "encoder.h.12.ln_1.bias": "pytorch_model-00001-of-00004.bin",
363
+ "encoder.h.12.ln_1.weight": "pytorch_model-00001-of-00004.bin",
364
+ "encoder.h.12.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
365
+ "encoder.h.12.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
366
+ "encoder.h.12.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
367
+ "encoder.h.12.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
368
+ "encoder.h.13.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
369
+ "encoder.h.13.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
370
+ "encoder.h.13.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
371
+ "encoder.h.13.ln_1.bias": "pytorch_model-00001-of-00004.bin",
372
+ "encoder.h.13.ln_1.weight": "pytorch_model-00001-of-00004.bin",
373
+ "encoder.h.13.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
374
+ "encoder.h.13.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
375
+ "encoder.h.13.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
376
+ "encoder.h.13.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
377
+ "encoder.h.14.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
378
+ "encoder.h.14.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
379
+ "encoder.h.14.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
380
+ "encoder.h.14.ln_1.bias": "pytorch_model-00001-of-00004.bin",
381
+ "encoder.h.14.ln_1.weight": "pytorch_model-00001-of-00004.bin",
382
+ "encoder.h.14.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
383
+ "encoder.h.14.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
384
+ "encoder.h.14.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
385
+ "encoder.h.14.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
386
+ "encoder.h.15.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
387
+ "encoder.h.15.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
388
+ "encoder.h.15.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
389
+ "encoder.h.15.ln_1.bias": "pytorch_model-00001-of-00004.bin",
390
+ "encoder.h.15.ln_1.weight": "pytorch_model-00001-of-00004.bin",
391
+ "encoder.h.15.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
392
+ "encoder.h.15.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
393
+ "encoder.h.15.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
394
+ "encoder.h.15.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
395
+ "encoder.h.16.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
396
+ "encoder.h.16.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
397
+ "encoder.h.16.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
398
+ "encoder.h.16.ln_1.bias": "pytorch_model-00001-of-00004.bin",
399
+ "encoder.h.16.ln_1.weight": "pytorch_model-00001-of-00004.bin",
400
+ "encoder.h.16.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
401
+ "encoder.h.16.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
402
+ "encoder.h.16.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
403
+ "encoder.h.16.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
404
+ "encoder.h.17.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
405
+ "encoder.h.17.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
406
+ "encoder.h.17.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
407
+ "encoder.h.17.ln_1.bias": "pytorch_model-00001-of-00004.bin",
408
+ "encoder.h.17.ln_1.weight": "pytorch_model-00001-of-00004.bin",
409
+ "encoder.h.17.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
410
+ "encoder.h.17.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
411
+ "encoder.h.17.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
412
+ "encoder.h.17.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
413
+ "encoder.h.18.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
414
+ "encoder.h.18.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
415
+ "encoder.h.18.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
416
+ "encoder.h.18.ln_1.bias": "pytorch_model-00001-of-00004.bin",
417
+ "encoder.h.18.ln_1.weight": "pytorch_model-00001-of-00004.bin",
418
+ "encoder.h.18.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
419
+ "encoder.h.18.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
420
+ "encoder.h.18.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
421
+ "encoder.h.18.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
422
+ "encoder.h.19.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
423
+ "encoder.h.19.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
424
+ "encoder.h.19.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
425
+ "encoder.h.19.ln_1.bias": "pytorch_model-00001-of-00004.bin",
426
+ "encoder.h.19.ln_1.weight": "pytorch_model-00001-of-00004.bin",
427
+ "encoder.h.19.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
428
+ "encoder.h.19.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
429
+ "encoder.h.19.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
430
+ "encoder.h.19.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
431
+ "encoder.h.2.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
432
+ "encoder.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
433
+ "encoder.h.2.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
434
+ "encoder.h.2.ln_1.bias": "pytorch_model-00001-of-00004.bin",
435
+ "encoder.h.2.ln_1.weight": "pytorch_model-00001-of-00004.bin",
436
+ "encoder.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
437
+ "encoder.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
438
+ "encoder.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
439
+ "encoder.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
440
+ "encoder.h.3.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
441
+ "encoder.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
442
+ "encoder.h.3.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
443
+ "encoder.h.3.ln_1.bias": "pytorch_model-00001-of-00004.bin",
444
+ "encoder.h.3.ln_1.weight": "pytorch_model-00001-of-00004.bin",
445
+ "encoder.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
446
+ "encoder.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
447
+ "encoder.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
448
+ "encoder.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
449
+ "encoder.h.4.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
450
+ "encoder.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
451
+ "encoder.h.4.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
452
+ "encoder.h.4.ln_1.bias": "pytorch_model-00001-of-00004.bin",
453
+ "encoder.h.4.ln_1.weight": "pytorch_model-00001-of-00004.bin",
454
+ "encoder.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
455
+ "encoder.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
456
+ "encoder.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
457
+ "encoder.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
458
+ "encoder.h.5.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
459
+ "encoder.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
460
+ "encoder.h.5.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
461
+ "encoder.h.5.ln_1.bias": "pytorch_model-00001-of-00004.bin",
462
+ "encoder.h.5.ln_1.weight": "pytorch_model-00001-of-00004.bin",
463
+ "encoder.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
464
+ "encoder.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
465
+ "encoder.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
466
+ "encoder.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
467
+ "encoder.h.6.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
468
+ "encoder.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
469
+ "encoder.h.6.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
470
+ "encoder.h.6.ln_1.bias": "pytorch_model-00001-of-00004.bin",
471
+ "encoder.h.6.ln_1.weight": "pytorch_model-00001-of-00004.bin",
472
+ "encoder.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
473
+ "encoder.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
474
+ "encoder.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
475
+ "encoder.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
476
+ "encoder.h.7.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
477
+ "encoder.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
478
+ "encoder.h.7.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
479
+ "encoder.h.7.ln_1.bias": "pytorch_model-00001-of-00004.bin",
480
+ "encoder.h.7.ln_1.weight": "pytorch_model-00001-of-00004.bin",
481
+ "encoder.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
482
+ "encoder.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
483
+ "encoder.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
484
+ "encoder.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
485
+ "encoder.h.8.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
486
+ "encoder.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
487
+ "encoder.h.8.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
488
+ "encoder.h.8.ln_1.bias": "pytorch_model-00001-of-00004.bin",
489
+ "encoder.h.8.ln_1.weight": "pytorch_model-00001-of-00004.bin",
490
+ "encoder.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
491
+ "encoder.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
492
+ "encoder.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
493
+ "encoder.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
494
+ "encoder.h.9.attn.causal_mask": "pytorch_model-00001-of-00004.bin",
495
+ "encoder.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
496
+ "encoder.h.9.attn.qkv_proj.weight": "pytorch_model-00001-of-00004.bin",
497
+ "encoder.h.9.ln_1.bias": "pytorch_model-00001-of-00004.bin",
498
+ "encoder.h.9.ln_1.weight": "pytorch_model-00001-of-00004.bin",
499
+ "encoder.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00004.bin",
500
+ "encoder.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00004.bin",
501
+ "encoder.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00004.bin",
502
+ "encoder.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00004.bin",
503
+ "encoder.ln_f.bias": "pytorch_model-00001-of-00004.bin",
504
+ "encoder.ln_f.weight": "pytorch_model-00001-of-00004.bin",
505
+ "encoder.wte.weight": "pytorch_model-00001-of-00004.bin"
506
+ }
507
+ }