robertgshaw2
commited on
Commit
•
29e8c23
1
Parent(s):
c7713ac
Update README.md
Browse files
README.md
CHANGED
@@ -63,7 +63,7 @@ For details on how this model was quantized and converted to marlin format, run
|
|
63 |
|
64 |
```bash
|
65 |
pip install -r quantization/requirements.txt
|
66 |
-
|
67 |
```
|
68 |
|
69 |
## Slack
|
|
|
63 |
|
64 |
```bash
|
65 |
pip install -r quantization/requirements.txt
|
66 |
+
python3 quantization/apply_gptq_save_marlin.py --model-id TinyLlama/TinyLlama-1.1B-Chat-v1.0 --save-dir ./tinyllama-marlin
|
67 |
```
|
68 |
|
69 |
## Slack
|