nampham1106 commited on
Commit
cf30a04
·
verified ·
1 Parent(s): 6413713

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +49 -0
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NewModel"
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
+ "rope_scaling": {
39
+ "factor": 8.0,
40
+ "type": "ntk"
41
+ },
42
+ "rope_theta": 20000,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.50.3",
45
+ "type_vocab_size": 1,
46
+ "unpad_inputs": false,
47
+ "use_memory_efficient_attention": false,
48
+ "vocab_size": 250048
49
+ }