lrl-modelcloud
commited on
Commit
•
03f465b
1
Parent(s):
40c9d1a
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
This model has been quantized using [GPTQModel](https://github.com/ModelCloud/GPTQModel).
|
2 |
+
|
3 |
+
- **bits**: 4
|
4 |
+
- **group_size**: 128
|
5 |
+
- **desc_act**: true
|
6 |
+
- **static_groups**: false
|
7 |
+
- **sym**: true
|
8 |
+
- **lm_head**: false
|
9 |
+
- **damp_percent**: 0.01
|
10 |
+
- **true_sequential**: true
|
11 |
+
- **model_name_or_path**: ""
|
12 |
+
- **model_file_base_name**: "model"
|
13 |
+
- **quant_method**: "gptq"
|
14 |
+
- **checkpoint_format**: "gptq"
|
15 |
+
- **meta**:
|
16 |
+
- **quantizer**: "gptqmodel:0.9.9-dev0"
|