Spaces:
Sleeping
Sleeping
ML Wong
commited on
Commit
·
597c86a
1
Parent(s):
477927e
Update model
Browse files- models/npc-bert-gpt2-best/config copy.json +0 -186
- models/npc-bert-gpt2-best/generation_config copy.json +0 -7
- models/npc-bert-gpt2-best/model copy.safetensors +0 -3
- models/npc-bert-gpt2-best/model.safetensors +1 -1
- npc_bert_models/__pycache__/__init__.cpython-310.pyc +0 -0
- npc_bert_models/__pycache__/cls_module.cpython-310.pyc +0 -0
- npc_bert_models/__pycache__/gradio_demo.cpython-310.pyc +0 -0
- npc_bert_models/__pycache__/mlm_module.cpython-310.pyc +0 -0
models/npc-bert-gpt2-best/config copy.json
DELETED
@@ -1,186 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"architectures": [
|
3 |
-
"EncoderDecoderModel"
|
4 |
-
],
|
5 |
-
"decoder": {
|
6 |
-
"_name_or_path": "openai-community/gpt2",
|
7 |
-
"activation_function": "gelu_new",
|
8 |
-
"add_cross_attention": true,
|
9 |
-
"architectures": [
|
10 |
-
"GPT2LMHeadModel"
|
11 |
-
],
|
12 |
-
"attn_pdrop": 0.1,
|
13 |
-
"bad_words_ids": null,
|
14 |
-
"begin_suppress_tokens": null,
|
15 |
-
"bos_token_id": 50256,
|
16 |
-
"chunk_size_feed_forward": 0,
|
17 |
-
"cross_attention_hidden_size": null,
|
18 |
-
"decoder_start_token_id": 5744,
|
19 |
-
"diversity_penalty": 0.0,
|
20 |
-
"do_sample": false,
|
21 |
-
"early_stopping": false,
|
22 |
-
"embd_pdrop": 0.1,
|
23 |
-
"encoder_no_repeat_ngram_size": 0,
|
24 |
-
"eos_token_id": 50256,
|
25 |
-
"exponential_decay_length_penalty": null,
|
26 |
-
"finetuning_task": null,
|
27 |
-
"forced_bos_token_id": null,
|
28 |
-
"forced_eos_token_id": null,
|
29 |
-
"id2label": {
|
30 |
-
"0": "LABEL_0",
|
31 |
-
"1": "LABEL_1"
|
32 |
-
},
|
33 |
-
"initializer_range": 0.02,
|
34 |
-
"is_decoder": true,
|
35 |
-
"is_encoder_decoder": false,
|
36 |
-
"label2id": {
|
37 |
-
"LABEL_0": 0,
|
38 |
-
"LABEL_1": 1
|
39 |
-
},
|
40 |
-
"layer_norm_epsilon": 1e-05,
|
41 |
-
"length_penalty": 1.0,
|
42 |
-
"max_length": 20,
|
43 |
-
"min_length": 0,
|
44 |
-
"model_type": "gpt2",
|
45 |
-
"n_ctx": 1024,
|
46 |
-
"n_embd": 768,
|
47 |
-
"n_head": 12,
|
48 |
-
"n_inner": null,
|
49 |
-
"n_layer": 12,
|
50 |
-
"n_positions": 1024,
|
51 |
-
"no_repeat_ngram_size": 0,
|
52 |
-
"num_beam_groups": 1,
|
53 |
-
"num_beams": 1,
|
54 |
-
"num_return_sequences": 1,
|
55 |
-
"output_attentions": false,
|
56 |
-
"output_hidden_states": false,
|
57 |
-
"output_scores": false,
|
58 |
-
"pad_token_id": null,
|
59 |
-
"prefix": null,
|
60 |
-
"problem_type": null,
|
61 |
-
"pruned_heads": {},
|
62 |
-
"remove_invalid_values": false,
|
63 |
-
"reorder_and_upcast_attn": false,
|
64 |
-
"repetition_penalty": 1.0,
|
65 |
-
"resid_pdrop": 0.1,
|
66 |
-
"return_dict": true,
|
67 |
-
"return_dict_in_generate": false,
|
68 |
-
"scale_attn_by_inverse_layer_idx": false,
|
69 |
-
"scale_attn_weights": true,
|
70 |
-
"sep_token_id": null,
|
71 |
-
"summary_activation": null,
|
72 |
-
"summary_first_dropout": 0.1,
|
73 |
-
"summary_proj_to_labels": true,
|
74 |
-
"summary_type": "cls_index",
|
75 |
-
"summary_use_proj": true,
|
76 |
-
"suppress_tokens": null,
|
77 |
-
"task_specific_params": {
|
78 |
-
"text-generation": {
|
79 |
-
"do_sample": true,
|
80 |
-
"max_length": 50
|
81 |
-
}
|
82 |
-
},
|
83 |
-
"temperature": 1.0,
|
84 |
-
"tf_legacy_loss": false,
|
85 |
-
"tie_encoder_decoder": false,
|
86 |
-
"tie_word_embeddings": true,
|
87 |
-
"tokenizer_class": null,
|
88 |
-
"top_k": 50,
|
89 |
-
"top_p": 1.0,
|
90 |
-
"torch_dtype": null,
|
91 |
-
"torchscript": false,
|
92 |
-
"typical_p": 1.0,
|
93 |
-
"use_bfloat16": false,
|
94 |
-
"use_cache": true,
|
95 |
-
"vocab_size": 50257
|
96 |
-
},
|
97 |
-
"decoder_start_token_id": 2,
|
98 |
-
"encoder": {
|
99 |
-
"_name_or_path": "gradio_demo/models/npc-bert-cls",
|
100 |
-
"add_cross_attention": false,
|
101 |
-
"architectures": [
|
102 |
-
"BertForSequenceClassification"
|
103 |
-
],
|
104 |
-
"attention_probs_dropout_prob": 0.1,
|
105 |
-
"bad_words_ids": null,
|
106 |
-
"begin_suppress_tokens": null,
|
107 |
-
"bos_token_id": 2,
|
108 |
-
"chunk_size_feed_forward": 0,
|
109 |
-
"classifier_dropout": null,
|
110 |
-
"cross_attention_hidden_size": null,
|
111 |
-
"decoder_start_token_id": null,
|
112 |
-
"diversity_penalty": 0.0,
|
113 |
-
"do_sample": false,
|
114 |
-
"early_stopping": false,
|
115 |
-
"encoder_no_repeat_ngram_size": 0,
|
116 |
-
"eos_token_id": 1,
|
117 |
-
"exponential_decay_length_penalty": null,
|
118 |
-
"finetuning_task": null,
|
119 |
-
"forced_bos_token_id": null,
|
120 |
-
"forced_eos_token_id": null,
|
121 |
-
"hidden_act": "gelu",
|
122 |
-
"hidden_dropout_prob": 0.1,
|
123 |
-
"hidden_size": 768,
|
124 |
-
"id2label": {
|
125 |
-
"0": "Benign/Healthy",
|
126 |
-
"1": "NPC",
|
127 |
-
"2": "Unknown/Out of Domain"
|
128 |
-
},
|
129 |
-
"initializer_range": 0.02,
|
130 |
-
"intermediate_size": 3072,
|
131 |
-
"is_decoder": false,
|
132 |
-
"is_encoder_decoder": false,
|
133 |
-
"label2id": {
|
134 |
-
"Benign/Healthy": 0,
|
135 |
-
"NPC": 1,
|
136 |
-
"Unknown/Out of Domain": 2
|
137 |
-
},
|
138 |
-
"layer_norm_eps": 1e-12,
|
139 |
-
"length_penalty": 1.0,
|
140 |
-
"max_length": 20,
|
141 |
-
"max_position_embeddings": 512,
|
142 |
-
"min_length": 0,
|
143 |
-
"model_type": "bert-generation",
|
144 |
-
"no_repeat_ngram_size": 0,
|
145 |
-
"num_attention_heads": 12,
|
146 |
-
"num_beam_groups": 1,
|
147 |
-
"num_beams": 1,
|
148 |
-
"num_hidden_layers": 12,
|
149 |
-
"num_return_sequences": 1,
|
150 |
-
"output_attentions": false,
|
151 |
-
"output_hidden_states": false,
|
152 |
-
"output_scores": false,
|
153 |
-
"pad_token_id": 0,
|
154 |
-
"position_embedding_type": "absolute",
|
155 |
-
"prefix": null,
|
156 |
-
"problem_type": "single_label_classification",
|
157 |
-
"pruned_heads": {},
|
158 |
-
"remove_invalid_values": false,
|
159 |
-
"repetition_penalty": 1.0,
|
160 |
-
"return_dict": true,
|
161 |
-
"return_dict_in_generate": false,
|
162 |
-
"sep_token_id": null,
|
163 |
-
"suppress_tokens": null,
|
164 |
-
"task_specific_params": null,
|
165 |
-
"temperature": 1.0,
|
166 |
-
"tf_legacy_loss": false,
|
167 |
-
"tie_encoder_decoder": false,
|
168 |
-
"tie_word_embeddings": true,
|
169 |
-
"tokenizer_class": null,
|
170 |
-
"top_k": 50,
|
171 |
-
"top_p": 1.0,
|
172 |
-
"torch_dtype": "float32",
|
173 |
-
"torchscript": false,
|
174 |
-
"type_vocab_size": 2,
|
175 |
-
"typical_p": 1.0,
|
176 |
-
"use_bfloat16": false,
|
177 |
-
"use_cache": true,
|
178 |
-
"vocab_size": 30522
|
179 |
-
},
|
180 |
-
"is_encoder_decoder": true,
|
181 |
-
"model_type": "encoder-decoder",
|
182 |
-
"pad_token_id": 0,
|
183 |
-
"torch_dtype": "float32",
|
184 |
-
"transformers_version": "4.37.2",
|
185 |
-
"vocab_size": 50257
|
186 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/npc-bert-gpt2-best/generation_config copy.json
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 50256,
|
4 |
-
"decoder_start_token_id": 5744,
|
5 |
-
"eos_token_id": 50256,
|
6 |
-
"transformers_version": "4.37.2"
|
7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/npc-bert-gpt2-best/model copy.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:015b17858751faf1b6d610a288bd5eb8179543e1925ff7a10a5a24a256ccd562
|
3 |
-
size 1046838512
|
|
|
|
|
|
|
|
models/npc-bert-gpt2-best/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1046838512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffa5b9e133f91b3757ce917312ddc5c57754cb4f5e94b6942bcf1cdc612f623f
|
3 |
size 1046838512
|
npc_bert_models/__pycache__/__init__.cpython-310.pyc
DELETED
Binary file (178 Bytes)
|
|
npc_bert_models/__pycache__/cls_module.cpython-310.pyc
DELETED
Binary file (3.44 kB)
|
|
npc_bert_models/__pycache__/gradio_demo.cpython-310.pyc
DELETED
Binary file (291 Bytes)
|
|
npc_bert_models/__pycache__/mlm_module.cpython-310.pyc
DELETED
Binary file (3.29 kB)
|
|