Update README.md
Browse files
README.md
CHANGED
|
@@ -58,3 +58,7 @@ if tokenizer.chat_template is not None:
|
|
| 58 |
|
| 59 |
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 60 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 60 |
```
|
| 61 |
+
|
| 62 |
+
Are you still reading down here? Really?
|
| 63 |
+
Ok, try this new Q4 lossless quant compression and tell us how to improve mlx-lm for 4-bit speed at 8-bit quality.
|
| 64 |
+
https://huggingface.co/NexaAIDev/DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant
|