Hugging Face's logo

MTSAIR
/
Cotype-Nano-4bit

Text Generation
Transformers
Safetensors
Russian
English
qwen2
conversational
text-generation-inference
Inference Endpoints
4-bit precision
awq
Model card Files Community
AlanRobotics commited on
Commit
9caed88
•
1 Parent(s): a5aef34

Upload Qwen2ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +2 -2
  2. generation_config.json +3 -3
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "nano_15_quant_v2",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
@@ -35,7 +35,7 @@
35
  "sliding_window": null,
36
  "tie_word_embeddings": true,
37
  "torch_dtype": "float16",
38
- "transformers_version": "4.45.2",
39
  "use_cache": false,
40
  "use_sliding_window": false,
41
  "vocab_size": 151936
 
1
  {
2
+ "_name_or_path": "nano_alignment_quant",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
 
35
  "sliding_window": null,
36
  "tie_word_embeddings": true,
37
  "torch_dtype": "float16",
38
+ "transformers_version": "4.46.2",
39
  "use_cache": false,
40
  "use_sliding_window": false,
41
  "vocab_size": 151936
generation_config.json CHANGED
@@ -7,8 +7,8 @@
7
  ],
8
  "pad_token_id": 151643,
9
  "repetition_penalty": 1.1,
10
- "temperature": 0.2,
11
  "top_k": 20,
12
- "top_p": 0.9,
13
- "transformers_version": "4.45.2"
14
  }
 
7
  ],
8
  "pad_token_id": 151643,
9
  "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
  "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.2"
14
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e29ea1e8778abf2ce8654bf7fb10c75fe5f5baaa1b20e17a7496a4d18aad515
3
  size 1135011144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d914618341373065ed76012adea9d28cc6c43143874a7c93763c2ea5fb6d92d
3
  size 1135011144