config.json
1.4 KB · 44 lines · json Raw
1 {
2 "architectures": [
3 "NewModel",
4 "NewForTokenClassification"
5 ],
6 "attention_probs_dropout_prob": 0.0,
7 "auto_map": {
8 "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9 "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
10 "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
11 "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12 "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13 "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14 "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15 },
16 "classifier_dropout": 0.0,
17 "hidden_act": "gelu",
18 "hidden_dropout_prob": 0.1,
19 "hidden_size": 768,
20 "initializer_range": 0.02,
21 "intermediate_size": 3072,
22 "layer_norm_eps": 1e-12,
23 "layer_norm_type": "layer_norm",
24 "max_position_embeddings": 8192,
25 "model_type": "new",
26 "num_attention_heads": 12,
27 "num_hidden_layers": 12,
28 "num_labels": 1,
29 "pack_qkv": true,
30 "pad_token_id": 1,
31 "position_embedding_type": "rope",
32 "rope_scaling": {
33 "factor": 8.0,
34 "type": "ntk"
35 },
36 "rope_theta": 20000,
37 "torch_dtype": "float16",
38 "transformers_version": "4.39.1",
39 "type_vocab_size": 1,
40 "unpad_inputs": false,
41 "use_memory_efficient_attention": false,
42 "vocab_size": 250048
43 }
44