quantized commit
Browse files- config.json +1 -1
- gptq_model-4bit-32g.safetensors +3 -0
- quantize_config.json +1 -1
config.json
CHANGED
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"bits": 4,
|
| 25 |
"damp_percent": 0.01,
|
| 26 |
"desc_act": false,
|
| 27 |
-
"group_size":
|
| 28 |
"is_marlin_format": false,
|
| 29 |
"model_file_base_name": null,
|
| 30 |
"model_name_or_path": null,
|
|
|
|
| 24 |
"bits": 4,
|
| 25 |
"damp_percent": 0.01,
|
| 26 |
"desc_act": false,
|
| 27 |
+
"group_size": 32,
|
| 28 |
"is_marlin_format": false,
|
| 29 |
"model_file_base_name": null,
|
| 30 |
"model_name_or_path": null,
|
gptq_model-4bit-32g.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:856bb495e289f22c556aca8938b285e4b2dcc82a4bf5ff489e40256d0b182346
|
| 3 |
+
size 1615499288
|
quantize_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bits": 4,
|
| 3 |
-
"group_size":
|
| 4 |
"damp_percent": 0.01,
|
| 5 |
"desc_act": false,
|
| 6 |
"static_groups": false,
|
|
|
|
| 1 |
{
|
| 2 |
"bits": 4,
|
| 3 |
+
"group_size": 32,
|
| 4 |
"damp_percent": 0.01,
|
| 5 |
"desc_act": false,
|
| 6 |
"static_groups": false,
|