lengocquangLAB commited on
Commit
f45cfcb
·
verified ·
1 Parent(s): dd969ca

Upload BartForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +17 -13
  2. generation_config.json +0 -3
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "_name_or_path": "facebook/bart-large-cnn",
3
- "_num_labels": 3,
4
- "activation_dropout": 0.0,
5
  "activation_function": "gelu",
 
6
  "add_final_layer_norm": false,
7
  "architectures": [
8
  "BartForConditionalGeneration"
9
  ],
10
- "attention_dropout": 0.0,
11
  "bos_token_id": 0,
12
- "classif_dropout": 0.0,
13
  "classifier_dropout": 0.0,
14
  "d_model": 1024,
15
  "decoder_attention_heads": 16,
@@ -24,7 +24,6 @@
24
  "encoder_layerdrop": 0.0,
25
  "encoder_layers": 12,
26
  "eos_token_id": 2,
27
- "force_bos_token_to_be_generated": true,
28
  "forced_eos_token_id": 2,
29
  "gradient_checkpointing": false,
30
  "id2label": {
@@ -39,27 +38,32 @@
39
  "LABEL_1": 1,
40
  "LABEL_2": 2
41
  },
42
- "length_penalty": null,
43
- "max_length": null,
44
  "max_position_embeddings": 1024,
45
- "min_length": null,
46
  "model_type": "bart",
47
  "no_repeat_ngram_size": null,
48
  "normalize_before": false,
49
  "num_beams": null,
50
  "num_hidden_layers": 12,
51
- "output_past": true,
52
  "pad_token_id": 1,
53
- "prefix": " ",
54
  "scale_embedding": false,
55
  "task_specific_params": {
56
  "summarization": {
57
- "early_stopping": true,
 
 
 
 
 
58
  "length_penalty": 2.0,
59
  "max_length": 142,
60
  "min_length": 56,
61
- "no_repeat_ngram_size": 3,
62
  "num_beams": 4
 
 
 
 
 
 
63
  }
64
  },
65
  "torch_dtype": "float32",
 
1
  {
2
+ "_name_or_path": "facebook/bart-large",
3
+ "activation_dropout": 0.1,
 
4
  "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
  "add_final_layer_norm": false,
7
  "architectures": [
8
  "BartForConditionalGeneration"
9
  ],
10
+ "attention_dropout": 0.1,
11
  "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
  "classifier_dropout": 0.0,
14
  "d_model": 1024,
15
  "decoder_attention_heads": 16,
 
24
  "encoder_layerdrop": 0.0,
25
  "encoder_layers": 12,
26
  "eos_token_id": 2,
 
27
  "forced_eos_token_id": 2,
28
  "gradient_checkpointing": false,
29
  "id2label": {
 
38
  "LABEL_1": 1,
39
  "LABEL_2": 2
40
  },
 
 
41
  "max_position_embeddings": 1024,
 
42
  "model_type": "bart",
43
  "no_repeat_ngram_size": null,
44
  "normalize_before": false,
45
  "num_beams": null,
46
  "num_hidden_layers": 12,
 
47
  "pad_token_id": 1,
 
48
  "scale_embedding": false,
49
  "task_specific_params": {
50
  "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
55
+ },
56
+ "summarization_cnn": {
57
  "length_penalty": 2.0,
58
  "max_length": 142,
59
  "min_length": 56,
 
60
  "num_beams": 4
61
+ },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
  }
68
  },
69
  "torch_dtype": "float32",
generation_config.json CHANGED
@@ -5,9 +5,6 @@
5
  "eos_token_id": 2,
6
  "forced_bos_token_id": 0,
7
  "forced_eos_token_id": 2,
8
- "length_penalty": 2.0,
9
- "max_length": 142,
10
- "min_length": 56,
11
  "no_repeat_ngram_size": 3,
12
  "num_beams": 4,
13
  "pad_token_id": 1,
 
5
  "eos_token_id": 2,
6
  "forced_bos_token_id": 0,
7
  "forced_eos_token_id": 2,
 
 
 
8
  "no_repeat_ngram_size": 3,
9
  "num_beams": 4,
10
  "pad_token_id": 1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:016c1cee41beb6bd5accf79fe1dcc2469007f679a7a75a2559d261438880009a
3
  size 1625426996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c58858ef2244e68289b81507b6a056e3f86072b5edf9573cb3ba1ab89eb35cbb
3
  size 1625426996