Hugging Face's logo

ykerido
/
lora-intent-classifier-bert-supplement

Safetensors
bert
Model card Files
xet
Community
ykerido commited on
Commit
bc9c1be
·
verified ·
1 Parent(s): ed3859a

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. category_mapping.json +34 -0
  2. config.json +57 -0
  3. label_mapping.json +34 -0
  4. lora_config.json +1 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +56 -0
  9. vocab.txt +0 -0
category_mapping.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "category_to_idx": {
3
+ "biology": 0,
4
+ "business": 1,
5
+ "chemistry": 2,
6
+ "computer science": 3,
7
+ "economics": 4,
8
+ "engineering": 5,
9
+ "health": 6,
10
+ "history": 7,
11
+ "law": 8,
12
+ "math": 9,
13
+ "other": 10,
14
+ "philosophy": 11,
15
+ "physics": 12,
16
+ "psychology": 13
17
+ },
18
+ "idx_to_category": {
19
+ "0": "biology",
20
+ "1": "business",
21
+ "2": "chemistry",
22
+ "3": "computer science",
23
+ "4": "economics",
24
+ "5": "engineering",
25
+ "6": "health",
26
+ "7": "history",
27
+ "8": "law",
28
+ "9": "math",
29
+ "10": "other",
30
+ "11": "philosophy",
31
+ "12": "physics",
32
+ "13": "psychology"
33
+ }
34
+ }
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "torch_dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "biology",
14
+ "1": "business",
15
+ "2": "chemistry",
16
+ "3": "computer science",
17
+ "4": "economics",
18
+ "5": "engineering",
19
+ "6": "health",
20
+ "7": "history",
21
+ "8": "law",
22
+ "9": "math",
23
+ "10": "other",
24
+ "11": "philosophy",
25
+ "12": "physics",
26
+ "13": "psychology"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "biology": 0,
32
+ "business": 1,
33
+ "chemistry": 2,
34
+ "computer science": 3,
35
+ "economics": 4,
36
+ "engineering": 5,
37
+ "health": 6,
38
+ "history": 7,
39
+ "law": 8,
40
+ "math": 9,
41
+ "other": 10,
42
+ "philosophy": 11,
43
+ "physics": 12,
44
+ "psychology": 13
45
+ },
46
+ "layer_norm_eps": 1e-12,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "bert",
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 12,
51
+ "pad_token_id": 0,
52
+ "position_embedding_type": "absolute",
53
+ "transformers_version": "4.57.3",
54
+ "type_vocab_size": 2,
55
+ "use_cache": true,
56
+ "vocab_size": 30522
57
+ }
label_mapping.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "category_to_idx": {
3
+ "biology": 0,
4
+ "business": 1,
5
+ "chemistry": 2,
6
+ "computer science": 3,
7
+ "economics": 4,
8
+ "engineering": 5,
9
+ "health": 6,
10
+ "history": 7,
11
+ "law": 8,
12
+ "math": 9,
13
+ "other": 10,
14
+ "philosophy": 11,
15
+ "physics": 12,
16
+ "psychology": 13
17
+ },
18
+ "idx_to_category": {
19
+ "0": "biology",
20
+ "1": "business",
21
+ "2": "chemistry",
22
+ "3": "computer science",
23
+ "4": "economics",
24
+ "5": "engineering",
25
+ "6": "health",
26
+ "7": "history",
27
+ "8": "law",
28
+ "9": "math",
29
+ "10": "other",
30
+ "11": "philosophy",
31
+ "12": "physics",
32
+ "13": "psychology"
33
+ }
34
+ }
lora_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"rank": 16, "alpha": 32, "dropout": 0.1, "target_modules": ["attention.self.query", "attention.self.value", "attention.output.dense", "intermediate.dense", "output.dense"]}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76985e9c9a7b623b2c98609785583918652d4ce1d9e1cea8cddd9698cedef2e0
3
+ size 437995560
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff