Hugging Face's logo

M4-ai
/
TinyMistral-248M-v3

Text Generation
Transformers
Safetensors
English
mistral
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
5
Locutusque commited on
Commit
6603ca6
•
1 Parent(s): 8857129

Upload MistralForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +4 -4
  2. config.json +4 -3
  3. generation_config.json +1 -1
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- license: apache-2.0
3
- language:
4
- - en
5
  datasets:
6
  - Locutusque/UltraTextbooks
7
- ---
 
 
 
 
1
  ---
 
 
 
2
  datasets:
3
  - Locutusque/UltraTextbooks
4
+ language:
5
+ - en
6
+ license: apache-2.0
7
+ ---
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
2
- "_name_or_path": "Locutusque/TinyMistral-248M-v2.5",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
 
9
  "hidden_act": "silu",
10
  "hidden_size": 1024,
11
  "initializer_range": 0.02,
@@ -19,8 +20,8 @@
19
  "rope_theta": 10000.0,
20
  "sliding_window": 32,
21
  "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.36.2",
24
  "use_cache": true,
25
  "vocab_size": 32005
26
  }
 
1
  {
2
+ "_name_or_path": "Locutusque/TinyMistral-248M",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
+ "head_dim": 32,
10
  "hidden_act": "silu",
11
  "hidden_size": 1024,
12
  "initializer_range": 0.02,
 
20
  "rope_theta": 10000.0,
21
  "sliding_window": 32,
22
  "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.45.2",
25
  "use_cache": true,
26
  "vocab_size": 32005
27
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.36.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.45.2"
6
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb9969350acb49480495906a9dd0a4c7e6ee93eb23f2bd6ca463f61dd87a60ee
3
+ size 496060688