hghaan commited on
Commit
c4fea2e
·
verified ·
1 Parent(s): 61d9c86

Upload 5 files

Browse files
config.json CHANGED
@@ -1,28 +1,50 @@
1
  {
2
  "architectures": [
3
- "PhoBertForPointwiseRanking"
4
  ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "classifier_dropout": null,
8
- "eos_token_id": 2,
9
- "gradient_checkpointing": false,
 
 
 
 
 
 
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
 
 
 
13
  "initializer_range": 0.02,
14
  "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 258,
17
- "model_type": "roberta",
 
 
 
 
 
 
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
 
20
  "pad_token_id": 1,
21
- "position_embedding_type": "absolute",
22
- "tokenizer_class": "PhobertTokenizer",
 
 
 
 
 
23
  "torch_dtype": "float32",
24
  "transformers_version": "4.51.1",
25
  "type_vocab_size": 1,
26
- "use_cache": true,
27
- "vocab_size": 64001
 
28
  }
 
1
  {
2
  "architectures": [
3
+ "NewForSequenceClassification"
4
  ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "auto_map": {
7
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
8
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
9
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
10
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
11
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
12
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
13
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
14
+ },
15
+ "classifier_dropout": 0.0,
16
  "hidden_act": "gelu",
17
  "hidden_dropout_prob": 0.1,
18
  "hidden_size": 768,
19
+ "id2label": {
20
+ "0": "LABEL_0"
21
+ },
22
  "initializer_range": 0.02,
23
  "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "layer_norm_type": "layer_norm",
29
+ "logn_attention_clip1": false,
30
+ "logn_attention_scale": false,
31
+ "max_position_embeddings": 8192,
32
+ "model_type": "new",
33
  "num_attention_heads": 12,
34
  "num_hidden_layers": 12,
35
+ "pack_qkv": true,
36
  "pad_token_id": 1,
37
+ "position_embedding_type": "rope",
38
+ "problem_type": "regression",
39
+ "rope_scaling": {
40
+ "factor": 8.0,
41
+ "type": "ntk"
42
+ },
43
+ "rope_theta": 20000,
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.51.1",
46
  "type_vocab_size": 1,
47
+ "unpad_inputs": false,
48
+ "use_memory_efficient_attention": false,
49
+ "vocab_size": 250048
50
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7fde856083c6d8d68cb596e638702e2e4cbd818f48046c1a29b4ab82fa7ced4
3
- size 540020276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c8af6db3399e6438630d2a47eef7337fd6848fc2f6747aec91c258c4d4dee7
3
+ size 1223854204
special_tokens_map.json CHANGED
@@ -1,9 +1,51 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": "<mask>",
6
- "pad_token": "<pad>",
7
- "sep_token": "</s>",
8
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bea3479edc0ed107960cd26c4921fc5a4456ee8fa9e52b2a88cc8c71231d66e5
3
- size 669188
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
+ size 17082999
tokenizer_config.json CHANGED
@@ -32,9 +32,9 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "64000": {
36
  "content": "<mask>",
37
- "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
@@ -42,14 +42,21 @@
42
  }
43
  },
44
  "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": false,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "extra_special_tokens": {},
49
  "mask_token": "<mask>",
50
- "model_max_length": 1000000000000000019884624838656,
 
 
51
  "pad_token": "<pad>",
 
 
52
  "sep_token": "</s>",
53
- "tokenizer_class": "PhobertTokenizer",
 
 
 
54
  "unk_token": "<unk>"
55
  }
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "250001": {
36
  "content": "<mask>",
37
+ "lstrip": true,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
 
42
  }
43
  },
44
  "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "extra_special_tokens": {},
49
  "mask_token": "<mask>",
50
+ "max_length": 512,
51
+ "model_max_length": 32768,
52
+ "pad_to_multiple_of": null,
53
  "pad_token": "<pad>",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
  "sep_token": "</s>",
57
+ "stride": 0,
58
+ "tokenizer_class": "XLMRobertaTokenizerFast",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
  "unk_token": "<unk>"
62
  }