Hugging Face's logo

SoooSlooow
/
bart-cnn

Transformers
Safetensors
bart
text2text-generation
Model card Files
xet
 Community
SoooSlooow commited on
Commit
a2e4989
·
1 Parent(s): 7fd2071

Training in progress, step 2000

Browse files
Files changed (3) hide show
  1. config.json +9 -10
  2. model.safetensors +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "facebook/bart-base",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
5
  "add_bias_logits": false,
@@ -11,18 +11,18 @@
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,
@@ -43,9 +43,8 @@
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": {
 
1
  {
2
+ "_name_or_path": "facebook/bart-large",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
5
  "add_bias_logits": false,
 
11
  "bos_token_id": 0,
12
  "classif_dropout": 0.1,
13
  "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
  "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
  "decoder_start_token_id": 2,
20
  "dropout": 0.1,
21
  "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
  "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
  "eos_token_id": 2,
27
  "forced_bos_token_id": 0,
28
  "forced_eos_token_id": 2,
 
43
  "model_type": "bart",
44
  "no_repeat_ngram_size": 3,
45
  "normalize_before": false,
 
46
  "num_beams": 4,
47
+ "num_hidden_layers": 12,
48
  "pad_token_id": 1,
49
  "scale_embedding": false,
50
  "task_specific_params": {
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fab7ef367dc691e11577730e4bd0d9400b0db03617afe9b3f6327f6ce27c5b0
3
- size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d616bfd85db4fd7a06b1f6af0cb8614e61dfc6d0a8866eb7fc9f37ef87ada57
3
+ size 1625426996
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c7d24309011e33054843c4d84a0ff0cefd9f3499cc2de48535bdc917227491d
3
  size 4347
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6decc43bd5d29cbf1f51877fc30f7463dc3d7ec744ab147b324706f92c46e2e3
3
  size 4347