anzorq commited on
Commit
ce2e5c4
1 Parent(s): c21d928

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +7 -35
  2. model.bin +3 -0
  3. shared_vocabulary.json +0 -0
config.json CHANGED
@@ -1,37 +1,9 @@
1
  {
2
- "_name_or_path": "anzorq/m2m100_1.2B_ft_ru-kbd_50K",
3
- "activation_dropout": 0.0,
4
- "activation_function": "relu",
5
- "architectures": [
6
- "M2M100ForConditionalGeneration"
7
- ],
8
- "attention_dropout": 0.1,
9
- "bos_token_id": 0,
10
- "d_model": 1024,
11
- "decoder_attention_heads": 16,
12
- "decoder_ffn_dim": 8192,
13
- "decoder_layerdrop": 0.05,
14
- "decoder_layers": 24,
15
- "decoder_start_token_id": 2,
16
- "dropout": 0.1,
17
- "early_stopping": true,
18
- "encoder_attention_heads": 16,
19
- "encoder_ffn_dim": 8192,
20
- "encoder_layerdrop": 0.05,
21
- "encoder_layers": 24,
22
- "eos_token_id": 2,
23
- "gradient_checkpointing": false,
24
- "init_std": 0.02,
25
- "is_encoder_decoder": true,
26
- "max_length": 200,
27
- "max_position_embeddings": 1024,
28
- "model_type": "m2m_100",
29
- "num_beams": 5,
30
- "num_hidden_layers": 24,
31
- "pad_token_id": 1,
32
- "scale_embedding": true,
33
- "torch_dtype": "float32",
34
- "transformers_version": "4.33.3",
35
- "use_cache": true,
36
- "vocab_size": 128112
37
  }
 
1
  {
2
+ "add_source_bos": false,
3
+ "add_source_eos": false,
4
+ "bos_token": "<s>",
5
+ "decoder_start_token": "</s>",
6
+ "eos_token": "</s>",
7
+ "layer_norm_epsilon": null,
8
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c5c3b45b2a6ca5f307901213904110a1f8ad769dd5183546eb2203191f8d81
3
+ size 1250146530
shared_vocabulary.json ADDED
The diff for this file is too large to render. See raw diff