Hugging Face's logo

mesolitica
/
malaysian-mistral-191M-4096

Text Generation
Transformers
Safetensors
Malay
mistral
text-generation-inference
Model card Files
xet
Community
huseinzol05 commited on
Commit
53194a6
·
1 Parent(s): f358a87

Upload MistralForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +3 -3
  2. generation_config.json +1 -1
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "pretrain-mistral-191M/checkpoint-31000",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
@@ -19,8 +19,8 @@
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.34.1",
24
  "use_cache": true,
25
  "vocab_size": 32000
26
  }
 
1
  {
2
+ "_name_or_path": "pretrain-mistral-191M/checkpoint-16200",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
 
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.35.2",
24
  "use_cache": true,
25
  "vocab_size": 32000
26
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.34.1"
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.35.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f5285b2814b59d84c36be8f772e5fb11f1a9b829cac51d09f1d54deded5df3f
3
- size 762956768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:047fe212237ad648a4e33051a34ba877f8d02a8ca7053e29eec177b008fdd311
3
+ size 381486704