NeMo
PyTorch
English
Hindi
nemotron
ravirajoshi commited on
Commit
c7089bb
1 Parent(s): b75935e

Upload 6 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/nemotron-4-mini-hindi-4b-base",
3
+ "architectures": [
4
+ "NemotronForCausalLM"
5
+ ],
6
+ "bos_token_id": 2,
7
+ "eos_token_id": 3,
8
+ "hidden_act": "relu2",
9
+ "hidden_size": 3072,
10
+ "initializer_range": 0.0134,
11
+ "intermediate_size": 9216,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "nemotron",
14
+ "num_attention_heads": 24,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "norm_eps": 1e-05,
18
+ "rope_theta": 10000,
19
+ "partial_rotary_factor": 0.5,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.32.0.dev0",
23
+ "use_cache": true,
24
+ "vocab_size": 256000,
25
+ "kv_channels": 128
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccbeab8852eeaec5b4d985bc9443a17445d6c48ee7c03a4028e6c6ab177c8470
3
+ size 7563378688
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>"
4
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d0648daa0467fb02ddef7ff25460321dab2fbb20c280ae0bc1ea8052f7df90
3
+ size 18143149
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dfd8b970f437002fc445214304969fe59e64d4f48500bd0b77ba55340f2d811
3
+ size 4545602
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff