Update README.md
Browse files
README.md
CHANGED
@@ -28,13 +28,14 @@ It is the result of quantising to 4bit using [AutoGPTQ](https://github.com/PanQi
|
|
28 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/CAMEL-33B-Combined-Data-GPTQ)
|
29 |
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/baichuan-inc/baichuan-7B)
|
30 |
|
31 |
-
## Experimental first GPTQ, requires latest
|
32 |
|
33 |
This is a first quantisation of a brand new model type.
|
34 |
|
35 |
It will only work with AutoGPTQ, and only using the latest version of AutoGPTQ, compiled from source
|
36 |
|
37 |
To merge this PR, please follow these steps to install the latest AutoGPTQ from source:
|
|
|
38 |
**Linux**
|
39 |
```
|
40 |
pip uninstall -y auto-gptq
|
|
|
28 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/CAMEL-33B-Combined-Data-GPTQ)
|
29 |
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/baichuan-inc/baichuan-7B)
|
30 |
|
31 |
+
## Experimental first GPTQ, requires latest AutoGPTQ code
|
32 |
|
33 |
This is a first quantisation of a brand new model type.
|
34 |
|
35 |
It will only work with AutoGPTQ, and only using the latest version of AutoGPTQ, compiled from source
|
36 |
|
37 |
To merge this PR, please follow these steps to install the latest AutoGPTQ from source:
|
38 |
+
|
39 |
**Linux**
|
40 |
```
|
41 |
pip uninstall -y auto-gptq
|