SamagraDataGov commited on
Commit
17fd1e3
·
verified ·
1 Parent(s): 4448d69

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -37,21 +37,6 @@
37
  "pad_token_id": 0,
38
  "position_embedding_type": "absolute",
39
  "problem_type": "single_label_classification",
40
- "quantization_config": {
41
- "_load_in_4bit": false,
42
- "_load_in_8bit": true,
43
- "bnb_4bit_compute_dtype": "float32",
44
- "bnb_4bit_quant_storage": "uint8",
45
- "bnb_4bit_quant_type": "fp4",
46
- "bnb_4bit_use_double_quant": false,
47
- "llm_int8_enable_fp32_cpu_offload": false,
48
- "llm_int8_has_fp16_weight": false,
49
- "llm_int8_skip_modules": null,
50
- "llm_int8_threshold": 6.0,
51
- "load_in_4bit": false,
52
- "load_in_8bit": true,
53
- "quant_method": "bitsandbytes"
54
- },
55
  "torch_dtype": "float16",
56
  "transformers_version": "4.41.1",
57
  "type_vocab_size": 2,
 
37
  "pad_token_id": 0,
38
  "position_embedding_type": "absolute",
39
  "problem_type": "single_label_classification",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  "torch_dtype": "float16",
41
  "transformers_version": "4.41.1",
42
  "type_vocab_size": 2,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70e3980f7c1a2f99647c950a1d24e7aeed6cdbcd50935d7630ba0d2788af9fc7
3
- size 133825319
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627fc91edf567c851511e26d11c5c19aa64ea2f4665aa08da95c7c3d0bb7f69e
3
+ size 218998662
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 512,
49
+ "model_max_length": 512,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff