Hugging Face's logo

reyvan
/
Qwen-7B-8bit

Text Generation
Transformers
PyTorch
qwen
custom_code
4-bit precision
gptq
Model card Files Community
reyvan commited on
Commit
94165f4
·
verified ·
1 Parent(s): 045dc76

Upload 3 files

Browse files
Files changed (2) hide show
  1. config.json +1 -1
  2. quantize_config.json +1 -1
config.json CHANGED
@@ -30,7 +30,7 @@
30
  "group_size": 128,
31
  "is_marlin_format": false,
32
  "model_file_base_name": "gptq_model-4bit-128g",
33
- "model_name_or_path": "Qwen-7B-4bit",
34
  "quant_method": "gptq",
35
  "static_groups": false,
36
  "sym": true,
 
30
  "group_size": 128,
31
  "is_marlin_format": false,
32
  "model_file_base_name": "gptq_model-4bit-128g",
33
+ "model_name_or_path": "Qwen-7B-125m-4bit-128g",
34
  "quant_method": "gptq",
35
  "static_groups": false,
36
  "sym": true,
quantize_config.json CHANGED
@@ -6,7 +6,7 @@
6
  "static_groups": false,
7
  "sym": true,
8
  "true_sequential": true,
9
- "model_name_or_path": "Qwen-7B-4bit",
10
  "model_file_base_name": "gptq_model-4bit-128g",
11
  "is_marlin_format": false,
12
  "quant_method": "gptq"
 
6
  "static_groups": false,
7
  "sym": true,
8
  "true_sequential": true,
9
+ "model_name_or_path": "Qwen-7B-125m-4bit-128g",
10
  "model_file_base_name": "gptq_model-4bit-128g",
11
  "is_marlin_format": false,
12
  "quant_method": "gptq"