Upload 6 files
Browse files- config.json +51 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "thunlp/Lawformer",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongformerForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"attention_window": [
|
| 8 |
+
512,
|
| 9 |
+
512,
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"bos_token_id": 0,
|
| 22 |
+
"classifier_dropout": null,
|
| 23 |
+
"directionality": "bidi",
|
| 24 |
+
"eos_token_id": 2,
|
| 25 |
+
"gradient_checkpointing": false,
|
| 26 |
+
"hidden_act": "gelu",
|
| 27 |
+
"hidden_dropout_prob": 0.1,
|
| 28 |
+
"hidden_size": 768,
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"max_position_embeddings": 4098,
|
| 33 |
+
"model_type": "longformer",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"onnx_export": false,
|
| 37 |
+
"output_past": true,
|
| 38 |
+
"pad_token_id": 1,
|
| 39 |
+
"pooler_fc_size": 768,
|
| 40 |
+
"pooler_num_attention_heads": 12,
|
| 41 |
+
"pooler_num_fc_layers": 3,
|
| 42 |
+
"pooler_size_per_head": 128,
|
| 43 |
+
"pooler_type": "first_token_transform",
|
| 44 |
+
"position_embedding_type": "absolute",
|
| 45 |
+
"sep_token_id": 2,
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.23.1",
|
| 48 |
+
"type_vocab_size": 2,
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"vocab_size": 21128
|
| 51 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11e8d3578dc0ed8f4541bf5677764e4ea4f3724dd3feb371798a891402f22e81
|
| 3 |
+
size 505316253
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": true,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"name_or_path": "hfl/chinese-roberta-wwm-ext",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"special_tokens_map_file": "/home/wanghao/.cache/huggingface/hub/models--hfl--chinese-roberta-wwm-ext/snapshots/5c58d0b8ec1d9014354d691c538661bf00bfdb44/special_tokens_map.json",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "BertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|