chore: upload
Browse files- model_architecture.json +1 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +58 -0
- vocab.txt +0 -0
model_architecture.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
"{\"class_name\": \"TFBertForSequenceClassification\", \"config\": {\"return_dict\": true, \"output_hidden_states\": false, \"output_attentions\": false, \"torchscript\": false, \"torch_dtype\": null, \"use_bfloat16\": false, \"tf_legacy_loss\": false, \"pruned_heads\": {}, \"tie_word_embeddings\": true, \"chunk_size_feed_forward\": 0, \"is_encoder_decoder\": false, \"is_decoder\": false, \"cross_attention_hidden_size\": null, \"add_cross_attention\": false, \"tie_encoder_decoder\": false, \"max_length\": 20, \"min_length\": 0, \"do_sample\": false, \"early_stopping\": false, \"num_beams\": 1, \"num_beam_groups\": 1, \"diversity_penalty\": 0.0, \"temperature\": 1.0, \"top_k\": 50, \"top_p\": 1.0, \"typical_p\": 1.0, \"repetition_penalty\": 1.0, \"length_penalty\": 1.0, \"no_repeat_ngram_size\": 0, \"encoder_no_repeat_ngram_size\": 0, \"bad_words_ids\": null, \"num_return_sequences\": 1, \"output_scores\": false, \"return_dict_in_generate\": false, \"forced_bos_token_id\": null, \"forced_eos_token_id\": null, \"remove_invalid_values\": false, \"exponential_decay_length_penalty\": null, \"suppress_tokens\": null, \"begin_suppress_tokens\": null, \"architectures\": [\"BertForMaskedLM\"], \"finetuning_task\": null, \"id2label\": {\"0\": \"LABEL_0\", \"1\": \"LABEL_1\"}, \"label2id\": {\"LABEL_0\": 0, \"LABEL_1\": 1}, \"tokenizer_class\": null, \"prefix\": null, \"bos_token_id\": null, \"pad_token_id\": 0, \"eos_token_id\": null, \"sep_token_id\": null, \"decoder_start_token_id\": null, \"task_specific_params\": null, \"problem_type\": null, \"_name_or_path\": \"bert-base-uncased\", \"_attn_implementation_autoset\": false, \"transformers_version\": \"4.48.3\", \"gradient_checkpointing\": false, \"model_type\": \"bert\", \"vocab_size\": 30522, \"hidden_size\": 768, \"num_hidden_layers\": 12, \"num_attention_heads\": 12, \"hidden_act\": \"gelu\", \"intermediate_size\": 3072, \"hidden_dropout_prob\": 0.1, \"attention_probs_dropout_prob\": 0.1, \"max_position_embeddings\": 512, \"type_vocab_size\": 2, \"initializer_range\": 0.02, \"layer_norm_eps\": 1e-12, \"position_embedding_type\": \"absolute\", \"use_cache\": true, \"classifier_dropout\": null}, \"keras_version\": \"2.18.0\", \"backend\": \"tensorflow\"}"
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|