Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Made by merging the following lora:
|
| 2 |
+
https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA
|
| 3 |
+
|
| 4 |
+
Then quantizing with ooba's old CUDA branch of GPTQ
|
| 5 |
+
```
|
| 6 |
+
python llama.py vicunlocked-30b c4 --wbits 4 --true-sequential --act-order --save_safetensors vicunlocked-30b-4bit.safetensors
|
| 7 |
+
```
|