Peter Henderson commited on
Commit
e6692c6
1 Parent(s): ecd825d
Files changed (5) hide show
  1. README.md +5 -0
  2. config.json +21 -0
  3. pytorch_model.bin +3 -0
  4. tokenizer_config.json +1 -0
  5. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ pipeline_tag: fill-mask
5
+ ---
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "legalbert-large-1.7M-1",
3
+ "attention_probs_dropout_prob": 0.1,
4
+ "directionality": "bidi",
5
+ "gradient_checkpointing": false,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 1024,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 4096,
11
+ "layer_norm_eps": 1e-12,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "bert",
14
+ "num_attention_heads": 16,
15
+ "num_hidden_layers": 24,
16
+ "pad_token_id": 0,
17
+ "transformers_version": "4.5.0",
18
+ "type_vocab_size": 2,
19
+ "use_cache": true,
20
+ "vocab_size": 32000
21
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e384228997ce6c26286b6c37bddc067e63c9a55b81d59a0630a582db7a9263ae
3
+ size 1351105910
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "handle_chinese_chars": true, "strip_accents": true, "name_or_path": "legalbert-large-1.7M-1"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff