valhalla HF staff commited on
Commit
b0c3779
1 Parent(s): 7652e0c

update mask token embeddings

Browse files
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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
+ "BartModel"
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_eos_token_id": 2,
28
+ "gradient_checkpointing": 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": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "normalize_embedding": true,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.12.0.dev0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "activation_dropout": 0.1,
3
  "activation_function": "gelu",
4
  "add_bias_logits": false,
@@ -66,7 +67,8 @@
66
  "num_beams": 6
67
  }
68
  },
69
- "transformers_version": "4.7.0.dev0",
 
70
  "use_cache": true,
71
  "vocab_size": 50265
72
  }
1
  {
2
+ "_name_or_path": "bart-base",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
5
  "add_bias_logits": false,
67
  "num_beams": 6
68
  }
69
  },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.12.0.dev0",
72
  "use_cache": true,
73
  "vocab_size": 50265
74
  }
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3164d4f102798fb6f9cca23d2b952d5251d2011195183f42725809a9479e798
3
  size 557690804
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53dd33667e5835469e2f7e32b51baf2356464ece3b80e3453a4febb83aa79752
3
  size 557690804
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c393f632913cdc64c13fcd1b039a74f17dd83cc3029c556802c0f2f8792b46f9
3
- size 557941479
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4fdb5e04114696ec4f7cc0cb5fc2a22a826f1c9eea234ca550b5390341a2fd
3
+ size 557771387
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e9ad2cdde27cb028e63c63624bad056157121964fe7110237e27ab30e5b3ae8
3
- size 557956240
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed6459d5365fb22f77ab71e7b27b1ff13fde4752d5600b449a1c1ad782bd286
3
+ size 557950280