staka commited on
Commit
f7ce112
1 Parent(s): 118baa5

Update models for transformers==4.30.*

Browse files
config.json CHANGED
@@ -11,13 +11,13 @@
11
  ]
12
  ],
13
  "bos_token_id": 0,
14
- "classifier_dropout": 0.0,
15
  "d_model": 512,
16
  "decoder_attention_heads": 8,
17
  "decoder_ffn_dim": 2048,
18
  "decoder_layerdrop": 0.0,
19
  "decoder_layers": 6,
20
  "decoder_start_token_id": 32000,
 
21
  "dropout": 0.1,
22
  "encoder_attention_heads": 8,
23
  "encoder_ffn_dim": 2048,
@@ -25,7 +25,6 @@
25
  "encoder_layers": 6,
26
  "eos_token_id": 0,
27
  "forced_eos_token_id": 0,
28
- "gradient_checkpointing": false,
29
  "init_std": 0.02,
30
  "is_encoder_decoder": true,
31
  "max_length": 512,
@@ -36,9 +35,10 @@
36
  "num_hidden_layers": 6,
37
  "pad_token_id": 32000,
38
  "scale_embedding": true,
 
39
  "static_position_embeddings": true,
40
  "torch_dtype": "float16",
41
- "transformers_version": "4.9.2",
42
  "use_cache": true,
43
  "vocab_size": 32001
44
  }
 
11
  ]
12
  ],
13
  "bos_token_id": 0,
 
14
  "d_model": 512,
15
  "decoder_attention_heads": 8,
16
  "decoder_ffn_dim": 2048,
17
  "decoder_layerdrop": 0.0,
18
  "decoder_layers": 6,
19
  "decoder_start_token_id": 32000,
20
+ "decoder_vocab_size": 32001,
21
  "dropout": 0.1,
22
  "encoder_attention_heads": 8,
23
  "encoder_ffn_dim": 2048,
 
25
  "encoder_layers": 6,
26
  "eos_token_id": 0,
27
  "forced_eos_token_id": 0,
 
28
  "init_std": 0.02,
29
  "is_encoder_decoder": true,
30
  "max_length": 512,
 
35
  "num_hidden_layers": 6,
36
  "pad_token_id": 32000,
37
  "scale_embedding": true,
38
+ "share_encoder_decoder_embeddings": true,
39
  "static_position_embeddings": true,
40
  "torch_dtype": "float16",
41
+ "transformers_version": "4.30.0",
42
  "use_cache": true,
43
  "vocab_size": 32001
44
  }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 32000
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 32000,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 12,
14
+ "pad_token_id": 32000,
15
+ "transformers_version": "4.30.0"
16
+ }
model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f711490e167fbc2a53ce671dc8835ddb459b12f61a730689af83f6ce4d0a9e75
3
- size 153908130
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:316522cd89f9292c7bdbe8ed37182191f1e515ea26163ae836dcafdfb68877e0
3
- size 153960131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e15d0b016255711ef06a3740933c3fa9eb7609a9c3e99d5326fbc7872a13729
3
+ size 121192965
source.spm CHANGED
Binary files a/source.spm and b/source.spm differ
 
special_tokens_map.json CHANGED
@@ -1 +1,5 @@
1
- {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm CHANGED
Binary files a/target.spm and b/target.spm differ
 
vocab.json CHANGED
The diff for this file is too large to render. See raw diff