Hugging Face's logo

ijwatson98
/
sft-t5-xsum-2303

Text2Text Generation
Transformers
Safetensors
bart
Inference Endpoints
Model card Files Community
ijwatson98 commited on
Commit
0cbf569
•
1 Parent(s): c2941b7

Upload BartForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +59 -45
  2. generation_config.json +11 -4
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,61 +1,75 @@
1
  {
2
- "_name_or_path": "google-t5/t5-base",
 
 
 
 
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
 
 
 
6
  "classifier_dropout": 0.0,
7
- "d_ff": 3072,
8
- "d_kv": 64,
9
  "d_model": 768,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "relu",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "relu",
15
- "initializer_factor": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  "is_encoder_decoder": true,
17
- "is_gated_act": false,
18
- "layer_norm_epsilon": 1e-06,
19
- "model_type": "t5",
20
- "n_positions": 512,
21
- "num_decoder_layers": 12,
22
- "num_heads": 12,
23
- "num_layers": 12,
24
- "output_past": true,
25
- "pad_token_id": 0,
26
- "relative_attention_max_distance": 128,
27
- "relative_attention_num_buckets": 32,
 
 
 
28
  "task_specific_params": {
29
  "summarization": {
30
- "early_stopping": true,
31
- "length_penalty": 2.0,
32
- "max_length": 200,
33
- "min_length": 30,
34
- "no_repeat_ngram_size": 3,
35
- "num_beams": 4,
36
- "prefix": "summarize: "
37
  },
38
- "translation_en_to_de": {
39
- "early_stopping": true,
40
- "max_length": 300,
41
- "num_beams": 4,
42
- "prefix": "translate English to German: "
43
- },
44
- "translation_en_to_fr": {
45
- "early_stopping": true,
46
- "max_length": 300,
47
- "num_beams": 4,
48
- "prefix": "translate English to French: "
49
  },
50
- "translation_en_to_ro": {
51
- "early_stopping": true,
52
- "max_length": 300,
53
- "num_beams": 4,
54
- "prefix": "translate English to Romanian: "
55
  }
56
  },
57
  "torch_dtype": "float32",
58
  "transformers_version": "4.38.2",
59
  "use_cache": false,
60
- "vocab_size": 32101
61
  }
 
1
  {
2
+ "_name_or_path": "facebook/bart-base",
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": 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
+ "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
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
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": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
  "task_specific_params": {
52
  "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
 
 
 
57
  },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
 
 
 
 
 
 
63
  },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
  }
70
  },
71
  "torch_dtype": "float32",
72
  "transformers_version": "4.38.2",
73
  "use_cache": false,
74
+ "vocab_size": 50265
75
  }
generation_config.json CHANGED
@@ -1,7 +1,14 @@
1
  {
2
  "_from_model_config": true,
3
- "decoder_start_token_id": 0,
4
- "eos_token_id": 1,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.38.2"
 
 
 
 
 
 
 
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.38.2",
13
+ "use_cache": false
14
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb3f88aa2d80df32e7dc9af8c9393f71554f0e802e61f281fec7332bc0d734a2
3
- size 891561768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:141c8ff9ff80ea6bf8ed807fb1cf55b0e5f2627e09e589ae57b2f6c9ebd5fb46
3
+ size 557912620