habdine commited on
Commit
b28f183
1 Parent(s): 85d1747

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 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prot2text_large",
3
+ "architectures": [
4
+ "Prot2TextModel"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_prot2text.Prot2TextConfig",
8
+ "AutoModel": "modeling_prot2text.Prot2TextModel",
9
+ "AutoModelForCausalLM": "modeling_prot2text.Prot2TextModel"
10
+ },
11
+ "model_type": "prot2text",
12
+ "bos_token_id": 50257,
13
+ "prot2text_version": "1.0",
14
+ "cross_esm_graph": true,
15
+ "decoder_start_token_id": 50257,
16
+ "early_stopping": true,
17
+ "eos_token_id": 50258,
18
+ "esm": true,
19
+ "esm_config": {
20
+ "_name_or_path": "facebook/esm2_t33_650M_UR50D",
21
+ "add_cross_attention": false,
22
+ "architectures": [
23
+ "EsmModel"
24
+ ],
25
+ "attention_probs_dropout_prob": 0.0,
26
+ "bad_words_ids": null,
27
+ "begin_suppress_tokens": null,
28
+ "bos_token_id": null,
29
+ "chunk_size_feed_forward": 0,
30
+ "classifier_dropout": null,
31
+ "cross_attention_hidden_size": null,
32
+ "decoder_start_token_id": null,
33
+ "diversity_penalty": 0.0,
34
+ "do_sample": false,
35
+ "early_stopping": false,
36
+ "emb_layer_norm_before": false,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": null,
39
+ "esmfold_config": null,
40
+ "exponential_decay_length_penalty": null,
41
+ "finetuning_task": null,
42
+ "forced_bos_token_id": null,
43
+ "forced_eos_token_id": null,
44
+ "hidden_act": "gelu",
45
+ "hidden_dropout_prob": 0.0,
46
+ "hidden_size": 1280,
47
+ "id2label": {
48
+ "0": "LABEL_0",
49
+ "1": "LABEL_1"
50
+ },
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 5120,
53
+ "is_decoder": false,
54
+ "is_encoder_decoder": false,
55
+ "is_folding_model": false,
56
+ "label2id": {
57
+ "LABEL_0": 0,
58
+ "LABEL_1": 1
59
+ },
60
+ "layer_norm_eps": 1e-05,
61
+ "length_penalty": 1.0,
62
+ "mask_token_id": 32,
63
+ "max_length": 20,
64
+ "max_position_embeddings": 1026,
65
+ "min_length": 0,
66
+ "model_type": "esm",
67
+ "no_repeat_ngram_size": 0,
68
+ "num_attention_heads": 20,
69
+ "num_beam_groups": 1,
70
+ "num_beams": 1,
71
+ "num_hidden_layers": 33,
72
+ "num_return_sequences": 1,
73
+ "output_attentions": false,
74
+ "output_hidden_states": false,
75
+ "output_scores": false,
76
+ "pad_token_id": 1,
77
+ "position_embedding_type": "rotary",
78
+ "prefix": null,
79
+ "problem_type": null,
80
+ "pruned_heads": {},
81
+ "remove_invalid_values": false,
82
+ "repetition_penalty": 1.0,
83
+ "return_dict": true,
84
+ "return_dict_in_generate": false,
85
+ "sep_token_id": null,
86
+ "suppress_tokens": null,
87
+ "task_specific_params": null,
88
+ "temperature": 1.0,
89
+ "tf_legacy_loss": false,
90
+ "tie_encoder_decoder": false,
91
+ "tie_word_embeddings": true,
92
+ "token_dropout": true,
93
+ "tokenizer_class": null,
94
+ "top_k": 50,
95
+ "top_p": 1.0,
96
+ "torch_dtype": "float32",
97
+ "torchscript": false,
98
+ "transformers_version": "4.30.1",
99
+ "typical_p": 1.0,
100
+ "use_bfloat16": false,
101
+ "use_cache": true,
102
+ "vocab_list": null,
103
+ "vocab_size": 33
104
+ },
105
+ "esm_model_name": "facebook/esm2_t33_650M_UR50D",
106
+ "gpt_config": {
107
+ "_name_or_path": "gpt2",
108
+ "prot2text_version": "1.0",
109
+ "activation_function": "gelu_new",
110
+ "add_cross_attention": true,
111
+ "architectures": [
112
+ "GPT2Model"
113
+ ],
114
+ "attn_pdrop": 0.1,
115
+ "bad_words_ids": null,
116
+ "begin_suppress_tokens": null,
117
+ "bos_token_id": 50257,
118
+ "chunk_size_feed_forward": 0,
119
+ "cross_attention_hidden_size": null,
120
+ "decoder_start_token_id": 50257,
121
+ "diversity_penalty": 0.0,
122
+ "do_sample": false,
123
+ "early_stopping": false,
124
+ "embd_pdrop": 0.1,
125
+ "encoder_no_repeat_ngram_size": 0,
126
+ "eos_token_id": 50258,
127
+ "exponential_decay_length_penalty": null,
128
+ "finetuning_task": null,
129
+ "forced_bos_token_id": null,
130
+ "forced_eos_token_id": null,
131
+ "id2label": {
132
+ "0": "LABEL_0",
133
+ "1": "LABEL_1"
134
+ },
135
+ "initializer_range": 0.02,
136
+ "is_decoder": false,
137
+ "is_encoder_decoder": true,
138
+ "label2id": {
139
+ "LABEL_0": 0,
140
+ "LABEL_1": 1
141
+ },
142
+ "layer_norm_epsilon": 1e-05,
143
+ "length_penalty": 1.0,
144
+ "max_length": 256,
145
+ "max_new_tokens": 256,
146
+ "min_length": 0,
147
+ "model_type": "gpt2",
148
+ "n_ctx": 1024,
149
+ "n_embd": 768,
150
+ "n_head": 12,
151
+ "n_inner": null,
152
+ "n_layer": 12,
153
+ "n_positions": 1024,
154
+ "no_repeat_ngram_size": 0,
155
+ "num_beam_groups": 1,
156
+ "num_beams": 1,
157
+ "num_return_sequences": 1,
158
+ "output_attentions": false,
159
+ "output_hidden_states": false,
160
+ "output_scores": false,
161
+ "pad_token_id": 50256,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "remove_invalid_values": false,
166
+ "reorder_and_upcast_attn": false,
167
+ "repetition_penalty": 1.0,
168
+ "resid_pdrop": 0.1,
169
+ "return_dict": true,
170
+ "return_dict_in_generate": false,
171
+ "scale_attn_by_inverse_layer_idx": false,
172
+ "scale_attn_weights": true,
173
+ "sep_token_id": null,
174
+ "summary_activation": null,
175
+ "summary_first_dropout": 0.1,
176
+ "summary_proj_to_labels": true,
177
+ "summary_type": "cls_index",
178
+ "summary_use_proj": true,
179
+ "suppress_tokens": null,
180
+ "task_specific_params": {
181
+ "text-generation": {
182
+ "do_sample": true,
183
+ "max_length": 50
184
+ }
185
+ },
186
+ "temperature": 1.0,
187
+ "tf_legacy_loss": false,
188
+ "tie_encoder_decoder": false,
189
+ "tie_word_embeddings": true,
190
+ "tokenizer_class": null,
191
+ "top_k": 50,
192
+ "top_p": 1.0,
193
+ "torch_dtype": "float32",
194
+ "torchscript": false,
195
+ "transformers_version": "4.30.1",
196
+ "typical_p": 1.0,
197
+ "use_bfloat16": false,
198
+ "use_cache": true,
199
+ "vocab_size": 50259
200
+ },
201
+ "gpt_model_name": "../data/gpt2/",
202
+ "length_penalty": 2.0,
203
+ "max_new_tokens": 256,
204
+ "no_repeat_ngram_size": 3,
205
+ "pad_token_id": 50256,
206
+ "rgcn": true,
207
+ "rgcn_input_dim": 67,
208
+ "rgcn_n_layers": 6,
209
+ "torch_dtype": "float32",
210
+ "transformers_version": "4.30.1"
211
+ }
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 sha256:854582619ffc92c43dc4caae8cc40d9983204d62df6dba5ac699040e4f408919
3
+ size 3610935253
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": "GPT2Tokenizer",
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