Update README.md
Browse files
README.md
CHANGED
|
@@ -37,5 +37,6 @@ response = generate(model, tokenizer, prompt="hello", verbose=True)
|
|
| 37 |
## Use with mlx_lm cli
|
| 38 |
|
| 39 |
```bash
|
|
|
|
| 40 |
python3 -m mlx_lm.generate --model mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit --prompt "<|im_start|>system\nYou are an accurate, educational, and helpful information assistant<|im_end|>\n<|im_start|>user\nWhat is the difference between awq vs gptq quantitization?<|im_end|>\n<|im_start|>assistant\n" --max-tokens 2048
|
| 41 |
```
|
|
|
|
| 37 |
## Use with mlx_lm cli
|
| 38 |
|
| 39 |
```bash
|
| 40 |
+
pip install -U mlx-lm
|
| 41 |
python3 -m mlx_lm.generate --model mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit --prompt "<|im_start|>system\nYou are an accurate, educational, and helpful information assistant<|im_end|>\n<|im_start|>user\nWhat is the difference between awq vs gptq quantitization?<|im_end|>\n<|im_start|>assistant\n" --max-tokens 2048
|
| 42 |
```
|