Update README.md
Browse files
README.md
CHANGED
|
@@ -59,9 +59,8 @@ Instructions:
|
|
| 59 |
```
|
| 60 |
|
| 61 |
## Quantization
|
| 62 |
-
For details on how this model was quantized and converted to marlin format,
|
| 63 |
|
| 64 |
-
Run the following
|
| 65 |
```bash
|
| 66 |
pip install -r quantization/requirements.txt
|
| 67 |
CUDA_VISIBLE_DEVICES=0 python3 quantization/apply_gptq_save_marlin.py --model-id TinyLlama/TinyLlama-1.1B-Chat-v1.0 --save-dir ./tinyllama-marlin
|
|
|
|
| 59 |
```
|
| 60 |
|
| 61 |
## Quantization
|
| 62 |
+
For details on how this model was quantized and converted to marlin format, run the `quantization/apply_gptq_save_marlin.py` script:
|
| 63 |
|
|
|
|
| 64 |
```bash
|
| 65 |
pip install -r quantization/requirements.txt
|
| 66 |
CUDA_VISIBLE_DEVICES=0 python3 quantization/apply_gptq_save_marlin.py --model-id TinyLlama/TinyLlama-1.1B-Chat-v1.0 --save-dir ./tinyllama-marlin
|