Upload 4 files
Browse files- config.json +34 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"aen_module": null,
|
| 4 |
+
"afn_module": null,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BiEncoderModel"
|
| 7 |
+
],
|
| 8 |
+
"aspects_size": null,
|
| 9 |
+
"attention_probs_dropout_prob": 0.1,
|
| 10 |
+
"bos_token_id": null,
|
| 11 |
+
"classifier_dropout": null,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"encoder_module": "BERT",
|
| 14 |
+
"eos_token_id": null,
|
| 15 |
+
"gradient_checkpointing": false,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.1,
|
| 18 |
+
"hidden_size": 768,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"is_decoder": false,
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"num_aspects": null,
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"pooler_module": "Linear",
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"transformers_version": "5.7.0",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"vocab_size": 30522
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58d09fec498a68c292081dd8a40e1f21982d8702642d2d42dc3c945fa64a48f6
|
| 3 |
+
size 437954480
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": true,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"max_length": 128,
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_to_multiple_of": null,
|
| 11 |
+
"pad_token": "[PAD]",
|
| 12 |
+
"pad_token_type_id": 0,
|
| 13 |
+
"padding_side": "right",
|
| 14 |
+
"sep_token": "[SEP]",
|
| 15 |
+
"stride": 0,
|
| 16 |
+
"strip_accents": null,
|
| 17 |
+
"tokenize_chinese_chars": true,
|
| 18 |
+
"tokenizer_class": "BertTokenizer",
|
| 19 |
+
"truncation_side": "right",
|
| 20 |
+
"truncation_strategy": "longest_first",
|
| 21 |
+
"unk_token": "[UNK]"
|
| 22 |
+
}
|