Upload folder using huggingface_hub
Browse files- README.md +36 -0
- added_tokens.json +3 -0
- config.json +62 -0
- mergekit_config.yml +17 -0
- model-00001-of-00001.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +72 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- xshubhamx/InLegalBERT
|
8 |
+
- xshubhamx/legal-bert-base-uncased
|
9 |
+
---
|
10 |
+
|
11 |
+
# UNTRAINED-InLegal-InLegal-legal-merge-ties-d-053-w-050
|
12 |
+
|
13 |
+
UNTRAINED-InLegal-InLegal-legal-merge-ties-d-053-w-050 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [xshubhamx/InLegalBERT](https://huggingface.co/xshubhamx/InLegalBERT)
|
15 |
+
* [xshubhamx/legal-bert-base-uncased](https://huggingface.co/xshubhamx/legal-bert-base-uncased)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yaml
|
20 |
+
models:
|
21 |
+
- model: xshubhamx/InLegalBERT
|
22 |
+
parameters:
|
23 |
+
density: 0.53
|
24 |
+
weight: 0.5
|
25 |
+
- model: xshubhamx/legal-bert-base-uncased
|
26 |
+
parameters:
|
27 |
+
density: 0.53
|
28 |
+
weight: 0.5
|
29 |
+
merge_method: ties
|
30 |
+
base_model: xshubhamx/REAL-InLegalBERT
|
31 |
+
parameters:
|
32 |
+
normalize: true
|
33 |
+
int8_mask: true
|
34 |
+
dtype: float16
|
35 |
+
|
36 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 30522
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xshubhamx/REAL-InLegalBERT",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "Issue",
|
15 |
+
"1": "Court Discourse",
|
16 |
+
"2": "Conclusion",
|
17 |
+
"3": "Precedent Analysis",
|
18 |
+
"4": "Section Analysis",
|
19 |
+
"5": "Argument by Petitioner",
|
20 |
+
"6": "Fact",
|
21 |
+
"7": "Argument by Respondent",
|
22 |
+
"8": "Ratio",
|
23 |
+
"9": "Appellant",
|
24 |
+
"10": "Respondent",
|
25 |
+
"11": "Argument by Appellant",
|
26 |
+
"12": "Petitioner",
|
27 |
+
"13": "Judge",
|
28 |
+
"14": "Argument by Defendant"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"Appellant": 9,
|
34 |
+
"Argument by Appellant": 11,
|
35 |
+
"Argument by Defendant": 14,
|
36 |
+
"Argument by Petitioner": 5,
|
37 |
+
"Argument by Respondent": 7,
|
38 |
+
"Conclusion": 2,
|
39 |
+
"Court Discourse": 1,
|
40 |
+
"Fact": 6,
|
41 |
+
"Issue": 0,
|
42 |
+
"Judge": 13,
|
43 |
+
"Petitioner": 12,
|
44 |
+
"Precedent Analysis": 3,
|
45 |
+
"Ratio": 8,
|
46 |
+
"Respondent": 10,
|
47 |
+
"Section Analysis": 4
|
48 |
+
},
|
49 |
+
"layer_norm_eps": 1e-12,
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"model_type": "bert",
|
52 |
+
"num_attention_heads": 12,
|
53 |
+
"num_hidden_layers": 12,
|
54 |
+
"output_past": true,
|
55 |
+
"pad_token_id": 30522,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"torch_dtype": "float16",
|
58 |
+
"transformers_version": "4.38.2",
|
59 |
+
"type_vocab_size": 2,
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 30523
|
62 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: xshubhamx/InLegalBERT
|
4 |
+
parameters:
|
5 |
+
density: 0.53
|
6 |
+
weight: 0.5
|
7 |
+
- model: xshubhamx/legal-bert-base-uncased
|
8 |
+
parameters:
|
9 |
+
density: 0.53
|
10 |
+
weight: 0.5
|
11 |
+
merge_method: ties
|
12 |
+
base_model: xshubhamx/REAL-InLegalBERT
|
13 |
+
parameters:
|
14 |
+
normalize: true
|
15 |
+
int8_mask: true
|
16 |
+
dtype: float16
|
17 |
+
|
model-00001-of-00001.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b532582b1251f6ed5190510a126c854edd3b3b858ef94c825f61581b9ea94aa
|
3 |
+
size 219012502
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 218989086}, "weight_map": {"classifier.weight": "model-00001-of-00001.safetensors", "classifier.bias": "model-00001-of-00001.safetensors", "bert.pooler.dense.bias": "model-00001-of-00001.safetensors", "bert.pooler.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.embeddings.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.embeddings.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.embeddings.word_embeddings.weight": "model-00001-of-00001.safetensors", "bert.embeddings.token_type_embeddings.weight": "model-00001-of-00001.safetensors", "bert.embeddings.position_embeddings.weight": "model-00001-of-00001.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"30522": {
|
44 |
+
"content": "<pad>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"clean_up_tokenization_spaces": true,
|
53 |
+
"cls_token": "[CLS]",
|
54 |
+
"do_basic_tokenize": true,
|
55 |
+
"do_lower_case": true,
|
56 |
+
"mask_token": "[MASK]",
|
57 |
+
"max_length": 512,
|
58 |
+
"model_max_length": 512,
|
59 |
+
"never_split": null,
|
60 |
+
"pad_to_multiple_of": null,
|
61 |
+
"pad_token": "<pad>",
|
62 |
+
"pad_token_type_id": 0,
|
63 |
+
"padding_side": "right",
|
64 |
+
"sep_token": "[SEP]",
|
65 |
+
"stride": 0,
|
66 |
+
"strip_accents": null,
|
67 |
+
"tokenize_chinese_chars": true,
|
68 |
+
"tokenizer_class": "BertTokenizer",
|
69 |
+
"truncation_side": "right",
|
70 |
+
"truncation_strategy": "longest_first",
|
71 |
+
"unk_token": "[UNK]"
|
72 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|