habdine commited on
Commit
931c438
1 Parent(s): b7d0e6b

Upload model and tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|graph_token|>": 50257,
3
+ "<|stop_token|>": 50258
4
+ }
config.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "esm2text_base",
3
+ "architectures": [
4
+ "Prot2TextModel"
5
+ ],
6
+ "bos_token_id": 50257,
7
+ "cross_esm_graph": false,
8
+ "decoder_start_token_id": 50257,
9
+ "early_stopping": true,
10
+ "eos_token_id": 50258,
11
+ "esm": true,
12
+ "esm_config": {
13
+ "_name_or_path": "facebook/esm2_t12_35M_UR50D",
14
+ "add_cross_attention": false,
15
+ "architectures": [
16
+ "EsmModel"
17
+ ],
18
+ "attention_probs_dropout_prob": 0.0,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": null,
22
+ "chunk_size_feed_forward": 0,
23
+ "classifier_dropout": null,
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
+ "emb_layer_norm_before": false,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": null,
32
+ "esmfold_config": null,
33
+ "exponential_decay_length_penalty": null,
34
+ "finetuning_task": null,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": null,
37
+ "hidden_act": "gelu",
38
+ "hidden_dropout_prob": 0.0,
39
+ "hidden_size": 480,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 1920,
46
+ "is_decoder": false,
47
+ "is_encoder_decoder": false,
48
+ "is_folding_model": false,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1
52
+ },
53
+ "layer_norm_eps": 1e-05,
54
+ "length_penalty": 1.0,
55
+ "mask_token_id": 32,
56
+ "max_length": 20,
57
+ "max_position_embeddings": 1026,
58
+ "min_length": 0,
59
+ "model_type": "esm",
60
+ "no_repeat_ngram_size": 0,
61
+ "num_attention_heads": 20,
62
+ "num_beam_groups": 1,
63
+ "num_beams": 1,
64
+ "num_hidden_layers": 12,
65
+ "num_return_sequences": 1,
66
+ "output_attentions": false,
67
+ "output_hidden_states": false,
68
+ "output_scores": false,
69
+ "pad_token_id": 1,
70
+ "position_embedding_type": "rotary",
71
+ "prefix": null,
72
+ "problem_type": null,
73
+ "pruned_heads": {},
74
+ "remove_invalid_values": false,
75
+ "repetition_penalty": 1.0,
76
+ "return_dict": true,
77
+ "return_dict_in_generate": false,
78
+ "sep_token_id": null,
79
+ "suppress_tokens": null,
80
+ "task_specific_params": null,
81
+ "temperature": 1.0,
82
+ "tf_legacy_loss": false,
83
+ "tie_encoder_decoder": false,
84
+ "tie_word_embeddings": true,
85
+ "token_dropout": true,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": "float32",
90
+ "torchscript": false,
91
+ "transformers_version": "4.30.1",
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": true,
95
+ "vocab_list": null,
96
+ "vocab_size": 33
97
+ },
98
+ "esm_model_name": "facebook/esm2_t12_35M_UR50D",
99
+ "gpt_config": {
100
+ "_name_or_path": "gpt2",
101
+ "activation_function": "gelu_new",
102
+ "add_cross_attention": true,
103
+ "architectures": [
104
+ "GPT2Model"
105
+ ],
106
+ "attn_pdrop": 0.1,
107
+ "bad_words_ids": null,
108
+ "begin_suppress_tokens": null,
109
+ "bos_token_id": 50257,
110
+ "chunk_size_feed_forward": 0,
111
+ "cross_attention_hidden_size": null,
112
+ "decoder_start_token_id": 50257,
113
+ "diversity_penalty": 0.0,
114
+ "do_sample": false,
115
+ "early_stopping": false,
116
+ "embd_pdrop": 0.1,
117
+ "encoder_no_repeat_ngram_size": 0,
118
+ "eos_token_id": 50258,
119
+ "exponential_decay_length_penalty": null,
120
+ "finetuning_task": null,
121
+ "forced_bos_token_id": null,
122
+ "forced_eos_token_id": null,
123
+ "id2label": {
124
+ "0": "LABEL_0",
125
+ "1": "LABEL_1"
126
+ },
127
+ "initializer_range": 0.02,
128
+ "is_decoder": false,
129
+ "is_encoder_decoder": true,
130
+ "label2id": {
131
+ "LABEL_0": 0,
132
+ "LABEL_1": 1
133
+ },
134
+ "layer_norm_epsilon": 1e-05,
135
+ "length_penalty": 1.0,
136
+ "max_length": 256,
137
+ "max_new_tokens": 256,
138
+ "min_length": 0,
139
+ "model_type": "gpt2",
140
+ "n_ctx": 1024,
141
+ "n_embd": 768,
142
+ "n_head": 12,
143
+ "n_inner": null,
144
+ "n_layer": 12,
145
+ "n_positions": 1024,
146
+ "no_repeat_ngram_size": 0,
147
+ "num_beam_groups": 1,
148
+ "num_beams": 1,
149
+ "num_return_sequences": 1,
150
+ "output_attentions": false,
151
+ "output_hidden_states": false,
152
+ "output_scores": false,
153
+ "pad_token_id": 50256,
154
+ "prefix": null,
155
+ "problem_type": null,
156
+ "prot2text_version": "1.1",
157
+ "pruned_heads": {},
158
+ "remove_invalid_values": false,
159
+ "reorder_and_upcast_attn": false,
160
+ "repetition_penalty": 1.0,
161
+ "resid_pdrop": 0.1,
162
+ "return_dict": true,
163
+ "return_dict_in_generate": false,
164
+ "scale_attn_by_inverse_layer_idx": false,
165
+ "scale_attn_weights": true,
166
+ "sep_token_id": null,
167
+ "summary_activation": null,
168
+ "summary_first_dropout": 0.1,
169
+ "summary_proj_to_labels": true,
170
+ "summary_type": "cls_index",
171
+ "summary_use_proj": true,
172
+ "suppress_tokens": null,
173
+ "task_specific_params": {
174
+ "text-generation": {
175
+ "do_sample": true,
176
+ "max_length": 50
177
+ }
178
+ },
179
+ "temperature": 1.0,
180
+ "tf_legacy_loss": false,
181
+ "tie_encoder_decoder": false,
182
+ "tie_word_embeddings": true,
183
+ "tokenizer_class": null,
184
+ "top_k": 50,
185
+ "top_p": 1.0,
186
+ "torch_dtype": "float32",
187
+ "torchscript": false,
188
+ "transformers_version": "4.30.1",
189
+ "typical_p": 1.0,
190
+ "use_bfloat16": false,
191
+ "use_cache": true,
192
+ "vocab_size": 50259
193
+ },
194
+ "gpt_model_name": "gpt2",
195
+ "length_penalty": 2.0,
196
+ "max_new_tokens": 256,
197
+ "no_repeat_ngram_size": 3,
198
+ "pad_token_id": 50256,
199
+ "prot2text_version": "1.1",
200
+ "rgcn": false,
201
+ "rgcn_input_dim": 67,
202
+ "rgcn_n_layers": 6,
203
+ "torch_dtype": "float32",
204
+ "transformers_version": "4.30.1"
205
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24098a6c4d6bfe08f9fc9046dc750e1c20deda2662e3b7aeb13eec308aaa9a49
3
+ size 903235197
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|graph_token|>",
3
+ "eos_token": "<|stop_token|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ }
12
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": null,
24
+ "tokenizer_class": "Prot2TextTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff