Hugging Face's logo

sglasher
/
my_awesome_qa_model

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
sglasher commited on
Commit
0006a1a
路
1 Parent(s): bef2c3e

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. config.json +23 -15
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +5 -2
  5. training_args.bin +1 -1
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,24 +1,32 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForQuestionAnswering"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
11
  "initializer_range": 0.02,
 
 
12
  "max_position_embeddings": 512,
13
- "model_type": "distilbert",
14
- "n_heads": 12,
15
- "n_layers": 6,
 
16
  "pad_token_id": 0,
17
- "qa_dropout": 0.1,
18
- "seq_classif_dropout": 0.2,
19
- "sinusoidal_pos_embds": false,
20
- "tie_weights_": true,
 
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.34.0",
23
- "vocab_size": 30522
 
 
24
  }
 
1
  {
2
+ "_name_or_path": "mrm8488/bert-multi-cased-finetuned-xquadv1",
 
3
  "architectures": [
4
+ "BertForQuestionAnswering"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
  "pad_token_id": 0,
21
+ "pooler_fc_size": 768,
22
+ "pooler_num_attention_heads": 12,
23
+ "pooler_num_fc_layers": 3,
24
+ "pooler_size_per_head": 128,
25
+ "pooler_type": "first_token_transform",
26
+ "position_embedding_type": "absolute",
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.34.0",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 119547
32
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a87ebaf030c799fa10a3839c0a63afb0efd4b6a8ad253cd40b399dd7929a7f
3
- size 265492517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0976abd91a8b17fdef4db7a57c9b055455b662d8000dab02597e679fd2fcf504
3
+ size 709125289
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -44,13 +44,16 @@
44
  "additional_special_tokens": [],
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
- "do_lower_case": true,
 
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": "DistilBertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
 
44
  "additional_special_tokens": [],
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
  "mask_token": "[MASK]",
50
+ "max_len": 512,
51
  "model_max_length": 512,
52
+ "never_split": null,
53
  "pad_token": "[PAD]",
54
  "sep_token": "[SEP]",
55
  "strip_accents": null,
56
  "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
  "unk_token": "[UNK]"
59
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b39b4c6543c2d08909fd9a8e63e5bfb8427deb5620fde5b5d649dba8c21f2893
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8871e31d277c4ccbea11ca3f253b8be05f3f7bcd665d35c07d5fde32631e3116
3
  size 4091
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff