Update README.md
Browse files
README.md
CHANGED
|
@@ -60,6 +60,7 @@ response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
|
| 60 |
Are you still reading down here?
|
| 61 |
|
| 62 |
Maybe check out this new Q4 lossless quant compression from NexaAI and tell the MLX community how to improve mlx-lm to get 8-bit quality at 4-bit speed!
|
|
|
|
| 63 |
[DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant](https://huggingface.co/NexaAIDev/DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant)
|
| 64 |
|
| 65 |
ore
|
|
|
|
| 60 |
Are you still reading down here?
|
| 61 |
|
| 62 |
Maybe check out this new Q4 lossless quant compression from NexaAI and tell the MLX community how to improve mlx-lm to get 8-bit quality at 4-bit speed!
|
| 63 |
+
|
| 64 |
[DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant](https://huggingface.co/NexaAIDev/DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant)
|
| 65 |
|
| 66 |
ore
|