StevenTang commited on
Commit
47f7570
1 Parent(s): df684ad

initial commit

Browse files
Files changed (6) hide show
  1. config.json +36 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +1 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "attention_dropout": 0.1,
5
+ "bos_token_id": 0,
6
+ "classifier_dropout": 0.0,
7
+ "d_model": 1024,
8
+ "decoder_attention_heads": 16,
9
+ "decoder_ffn_dim": 4096,
10
+ "decoder_layerdrop": 0.0,
11
+ "decoder_layers": 12,
12
+ "decoder_start_token_id": 2,
13
+ "dropout": 0.1,
14
+ "early_stopping": true,
15
+ "encoder_attention_heads": 16,
16
+ "encoder_ffn_dim": 4096,
17
+ "encoder_layerdrop": 0.0,
18
+ "encoder_layers": 12,
19
+ "eos_token_id": 2,
20
+ "forced_eos_token_id": 2,
21
+ "forced_bos_token_id": 0,
22
+ "gradient_checkpointing": false,
23
+ "init_std": 0.02,
24
+ "is_encoder_decoder": true,
25
+ "max_position_embeddings": 1024,
26
+ "model_type": "mvp",
27
+ "no_repeat_ngram_size": 3,
28
+ "num_beams": 5,
29
+ "pad_token_id": 1,
30
+ "scale_embedding": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.16.2",
33
+ "use_cache": true,
34
+ "use_prompt": false,
35
+ "vocab_size": 50267
36
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14ff87359377b5dcf53521829068600e8ad7f72f10684a725de91069afbd8d6
3
+ size 1625538817
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 1024}
vocab.json ADDED
The diff for this file is too large to render. See raw diff