Showing
10 changed files
with
138 additions
and
0 deletions
| 1 | +{ | ||
| 2 | + "word_embedding_dimension": 768, | ||
| 3 | + "pooling_mode_cls_token": false, | ||
| 4 | + "pooling_mode_mean_tokens": true, | ||
| 5 | + "pooling_mode_max_tokens": false, | ||
| 6 | + "pooling_mode_mean_sqrt_len_tokens": false, | ||
| 7 | + "pooling_mode_weightedmean_tokens": false, | ||
| 8 | + "pooling_mode_lasttoken": false, | ||
| 9 | + "include_prompt": true | ||
| 10 | +} |
model_pro/sentence_bert_model/config.json
0 → 100644
| 1 | +{ | ||
| 2 | + "_name_or_path": "./bert_model", | ||
| 3 | + "architectures": [ | ||
| 4 | + "BertModel" | ||
| 5 | + ], | ||
| 6 | + "attention_probs_dropout_prob": 0.1, | ||
| 7 | + "classifier_dropout": null, | ||
| 8 | + "directionality": "bidi", | ||
| 9 | + "hidden_act": "gelu", | ||
| 10 | + "hidden_dropout_prob": 0.1, | ||
| 11 | + "hidden_size": 768, | ||
| 12 | + "initializer_range": 0.02, | ||
| 13 | + "intermediate_size": 3072, | ||
| 14 | + "layer_norm_eps": 1e-12, | ||
| 15 | + "max_position_embeddings": 512, | ||
| 16 | + "model_type": "bert", | ||
| 17 | + "num_attention_heads": 12, | ||
| 18 | + "num_hidden_layers": 12, | ||
| 19 | + "pad_token_id": 0, | ||
| 20 | + "pooler_fc_size": 768, | ||
| 21 | + "pooler_num_attention_heads": 12, | ||
| 22 | + "pooler_num_fc_layers": 3, | ||
| 23 | + "pooler_size_per_head": 128, | ||
| 24 | + "pooler_type": "first_token_transform", | ||
| 25 | + "position_embedding_type": "absolute", | ||
| 26 | + "torch_dtype": "float32", | ||
| 27 | + "transformers_version": "4.37.2", | ||
| 28 | + "type_vocab_size": 2, | ||
| 29 | + "use_cache": true, | ||
| 30 | + "vocab_size": 21128 | ||
| 31 | +} |
model_pro/sentence_bert_model/modules.json
0 → 100644
model_pro/sentence_bert_model/readme.md
0 → 100644
model_pro/sentence_bert_model/tokenizer.json
0 → 100644
This diff could not be displayed because it is too large.
| 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": false, | ||
| 48 | + "mask_token": "[MASK]", | ||
| 49 | + "model_max_length": 512, | ||
| 50 | + "never_split": null, | ||
| 51 | + "pad_token": "[PAD]", | ||
| 52 | + "sep_token": "[SEP]", | ||
| 53 | + "strip_accents": null, | ||
| 54 | + "tokenize_chinese_chars": true, | ||
| 55 | + "tokenizer_class": "BertTokenizer", | ||
| 56 | + "unk_token": "[UNK]" | ||
| 57 | +} |
model_pro/sentence_bert_model/vocab.txt
0 → 100644
This diff could not be displayed because it is too large.
-
Please register or login to post a comment