Commit
·
bef9c7e
1
Parent(s):
4489deb
replace GPTQ with act order false (for faster generation)
Browse files- gptq_model-4bit-128g.safetensors +1 -1
- quantize_config.json +1 -1
gptq_model-4bit-128g.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3896714576
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b571df7dbd20b9e20455a5e9bfd01795779fed8176e98c9d1fee758e95a6a585
|
| 3 |
size 3896714576
|
quantize_config.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"bits": 4,
|
| 3 |
"group_size": 128,
|
| 4 |
"damp_percent": 0.01,
|
| 5 |
-
"desc_act":
|
| 6 |
"sym": true,
|
| 7 |
"true_sequential": true,
|
| 8 |
"model_name_or_path": null,
|
|
|
|
| 2 |
"bits": 4,
|
| 3 |
"group_size": 128,
|
| 4 |
"damp_percent": 0.01,
|
| 5 |
+
"desc_act": false,
|
| 6 |
"sym": true,
|
| 7 |
"true_sequential": true,
|
| 8 |
"model_name_or_path": null,
|