barthez / config.json
1 {
2 "activation_dropout": 0.1,
3 "activation_function": "gelu",
4 "add_bias_logits": false,
5 "add_final_layer_norm": true,
6 "architectures": [
7 "MBartForConditionalGeneration"
8 ],
9 "attention_dropout": 0.1,
10 "bos_token_id": 0,
11 "classif_dropout": 0.1,
12 "classifier_dropout": 0.0,
13 "d_model": 768,
14 "decoder_attention_heads": 12,
15 "decoder_ffn_dim": 3072,
16 "decoder_layerdrop": 0.0,
17 "decoder_layers": 6,
18 "decoder_start_token_id": 2,
19 "do_blenderbot_90_layernorm": false,
20 "dropout": 0.1,
21 "early_stopping": true,
22 "encoder_attention_heads": 12,
23 "encoder_ffn_dim": 3072,
24 "encoder_layerdrop": 0.0,
25 "encoder_layers": 6,
26 "eos_token_id": 2,
27 "extra_pos_embeddings": 2,
28 "force_bos_token_to_be_generated": false,
29 "id2label": {
30 "0": "LABEL_0",
31 "1": "LABEL_1",
32 "2": "LABEL_2"
33 },
34 "init_std": 0.02,
35 "is_encoder_decoder": true,
36 "label2id": {
37 "LABEL_0": 0,
38 "LABEL_1": 1,
39 "LABEL_2": 2
40 },
41 "max_position_embeddings": 1024,
42 "model_type": "mbart",
43 "no_repeat_ngram_size": 3,
44 "normalize_before": true,
45 "normalize_embedding": true,
46 "num_beams": 4,
47 "num_hidden_layers": 6,
48 "pad_token_id": 1,
49 "scale_embedding": false,
50 "static_position_embeddings": false,
51 "vocab_size": 50002,
52 "tokenizer_class": "BarthezTokenizer"
53 }
54