Warning re GPTQ files not working
Browse files
README.md
CHANGED
|
@@ -3,6 +3,10 @@ This repo contains the weights of the Koala 7B model produced at Berkeley. It is
|
|
| 3 |
|
| 4 |
This version has then been quantized to 4bit using https://github.com/qwopqwop200/GPTQ-for-LLaMa
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
Quantization command was:
|
| 7 |
```
|
| 8 |
python3 llama.py /content/koala-7B-HF c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save /content/koala-7B-4bit-128g.pt
|
|
|
|
| 3 |
|
| 4 |
This version has then been quantized to 4bit using https://github.com/qwopqwop200/GPTQ-for-LLaMa
|
| 5 |
|
| 6 |
+
### WARNING: At the present time the GPTQ files uploaded here are producing garbage output. It is not recommended to use them.
|
| 7 |
+
|
| 8 |
+
I'm working on diagnosing this issue and producing working files.
|
| 9 |
+
|
| 10 |
Quantization command was:
|
| 11 |
```
|
| 12 |
python3 llama.py /content/koala-7B-HF c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save /content/koala-7B-4bit-128g.pt
|