Hugging Face's logo

m-biriuchinskii
/
sarcasm_BARThez

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Mikhail Biriuchinskii commited on
Commit
fa52d2c
•
1 Parent(s): 25e9379

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +59 -24
config.json CHANGED
@@ -1,29 +1,64 @@
1
- {
 
 
 
 
 
2
  "architectures": [
3
- "DistilBertForSequenceClassification"
4
  ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "directionality": "bidi",
7
- "hidden_act": "gelu",
8
- "hidden_dropout_prob": 0.1,
9
- "hidden_size": 768,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 3072,
12
- "layer_norm_eps": 1e-12,
13
- "max_position_embeddings": 512,
14
- "model_type": "distilbert",
15
- "num_attention_heads": 12,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  "num_hidden_layers": 6,
17
- "output_past": true,
18
- "pad_token_id": 0,
19
- "pooler_fc_size": 768,
20
- "pooler_num_attention_heads": 12,
21
- "pooler_num_fc_layers": 3,
22
- "pooler_size_per_head": 128,
23
- "pooler_type": "first_token_transform",
24
- "position_embedding_type": "absolute",
25
- "transformers_version": "4.10.0",
26
- "type_vocab_size": 2,
 
 
 
 
 
27
  "use_cache": true,
28
- "vocab_size": 30522
29
  }
 
1
+ MBartConfig {
2
+ "_name_or_path": "moussaKam/barthez-orangesum-abstract",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
  "architectures": [
8
+ "MBartForConditionalGeneration"
9
  ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
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
+ "forced_eos_token_id": 2,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "mbart",
44
+ "normalize_before": true,
45
+ "normalize_embedding": true,
46
  "num_hidden_layers": 6,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": false,
49
+ "static_position_embeddings": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "early_stopping": true,
53
+ "length_penalty": 2.0,
54
+ "max_length": 100,
55
+ "min_length": 10,
56
+ "no_repeat_ngram_size": 3,
57
+ "num_beams": 4
58
+ }
59
+ },
60
+ "tokenizer_class": "BarthezTokenizer",
61
+ "transformers_version": "4.38.1",
62
  "use_cache": true,
63
+ "vocab_size": 50002
64
  }