Update README.md
Browse files
README.md
CHANGED
@@ -37,15 +37,15 @@ Open the text-generation-webui UI as normal.
|
|
37 |
|
38 |
## Provided files
|
39 |
|
40 |
-
**Compatible file -
|
41 |
|
42 |
-
In the `main` branch - the default one - you will find `
|
43 |
|
44 |
This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility
|
45 |
|
46 |
It was created without the `--act-order` parameter. It may have slightly lower inference quality compared to the other file, but is guaranteed to work on all versions of GPTQ-for-LLaMa and text-generation-webui.
|
47 |
|
48 |
-
* `
|
49 |
* Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
|
50 |
* Works with text-generation-webui one-click-installers
|
51 |
* Parameters: Groupsize = 128g. No act-order.
|
|
|
37 |
|
38 |
## Provided files
|
39 |
|
40 |
+
**Compatible file - wizard-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors**
|
41 |
|
42 |
+
In the `main` branch - the default one - you will find `wizard-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors`
|
43 |
|
44 |
This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility
|
45 |
|
46 |
It was created without the `--act-order` parameter. It may have slightly lower inference quality compared to the other file, but is guaranteed to work on all versions of GPTQ-for-LLaMa and text-generation-webui.
|
47 |
|
48 |
+
* `wizard-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors`
|
49 |
* Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
|
50 |
* Works with text-generation-webui one-click-installers
|
51 |
* Parameters: Groupsize = 128g. No act-order.
|