Update README.md
Browse files
README.md
CHANGED
|
@@ -2,10 +2,16 @@ Merge of [SuperHOT-LoRA-prototype](https://huggingface.co/kaiokendev/SuperHOT-Lo
|
|
| 2 |
|
| 3 |
|
| 4 |
Llama30B-SuperHOT-4bit-128g.safetensors Quantization:
|
|
|
|
| 5 |
CUDA_VISIBLE_DEVICES=0 python llama.py ausboss/Llama30B-SuperHOT c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors Llama30B-SuperHOT-4bit-128g.safetensors
|
| 6 |
-
|
| 7 |
Llama30B-SuperHOT-4bit.safetensors Quantization:
|
|
|
|
| 8 |
CUDA_VISIBLE_DEVICES=0 python llama.py ausboss/Llama30B-SuperHOT c4 --wbits 4 --true-sequential --save_safetensors Llama30B-SuperHOT-4bit.safetensors
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
|
| 11 |
|
|
|
|
| 2 |
|
| 3 |
|
| 4 |
Llama30B-SuperHOT-4bit-128g.safetensors Quantization:
|
| 5 |
+
```
|
| 6 |
CUDA_VISIBLE_DEVICES=0 python llama.py ausboss/Llama30B-SuperHOT c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors Llama30B-SuperHOT-4bit-128g.safetensors
|
| 7 |
+
```
|
| 8 |
Llama30B-SuperHOT-4bit.safetensors Quantization:
|
| 9 |
+
```
|
| 10 |
CUDA_VISIBLE_DEVICES=0 python llama.py ausboss/Llama30B-SuperHOT c4 --wbits 4 --true-sequential --save_safetensors Llama30B-SuperHOT-4bit.safetensors
|
| 11 |
+
```
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
|
| 16 |
|
| 17 |
|