jaygala24 commited on
Commit
e1b70f6
1 Parent(s): c0b09bd

Upload IndicTransForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +40 -0
  2. generation_config.json +8 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/jaygala/it2_ckpts/hf_distilled_models/indic-indic",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "IndicTransForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "decoder_attention_heads": 8,
11
+ "decoder_embed_dim": 512,
12
+ "decoder_ffn_dim": 2048,
13
+ "decoder_layerdrop": 0,
14
+ "decoder_layers": 18,
15
+ "decoder_normalize_before": true,
16
+ "decoder_start_token_id": 2,
17
+ "decoder_vocab_size": 122672,
18
+ "dropout": 0.2,
19
+ "encoder_attention_heads": 8,
20
+ "encoder_embed_dim": 512,
21
+ "encoder_ffn_dim": 2048,
22
+ "encoder_layerdrop": 0,
23
+ "encoder_layers": 18,
24
+ "encoder_normalize_before": true,
25
+ "encoder_vocab_size": 122706,
26
+ "eos_token_id": 2,
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "layernorm_embedding": true,
30
+ "max_source_positions": 256,
31
+ "max_target_positions": 256,
32
+ "model_type": "IndicTrans",
33
+ "num_hidden_layers": 18,
34
+ "pad_token_id": 1,
35
+ "scale_embedding": true,
36
+ "share_decoder_input_output_embed": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.34.0.dev0",
39
+ "use_cache": true
40
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.34.0.dev0"
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2731fe0aecdf6f02f3b015d988add8061c102e24a71b16bfa46383ce557dc36f
3
+ size 1283695433