Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,13 @@ base_model: FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview
|
|
| 7 |
|
| 8 |
# bobig/FuseO1-R1-QwQ-SkyT1-Flash-32B-Q8
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
The Model [bobig/FuseO1-R1-QwQ-SkyT1-Flash-32B-Q8](https://huggingface.co/bobig/FuseO1-R1-QwQ-SkyT1-Flash-32B-Q8) was
|
| 11 |
converted to MLX format from [FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview](https://huggingface.co/FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview)
|
| 12 |
using mlx-lm version **0.21.4**.
|
|
|
|
| 7 |
|
| 8 |
# bobig/FuseO1-R1-QwQ-SkyT1-Flash-32B-Q8
|
| 9 |
|
| 10 |
+
Quant made with the latest mlx-lm
|
| 11 |
+
|
| 12 |
+
This model is very good, my 2nd favorite for unpluged coding on Macs.
|
| 13 |
+
SpecDec works with this draft model [DeepScaleR-1.5B-Preview-Q8](https://huggingface.co/mlx-community/DeepScaleR-1.5B-Preview-Q8)
|
| 14 |
+
but the acceptance rate is only 61%.
|
| 15 |
+
|
| 16 |
+
|
| 17 |
The Model [bobig/FuseO1-R1-QwQ-SkyT1-Flash-32B-Q8](https://huggingface.co/bobig/FuseO1-R1-QwQ-SkyT1-Flash-32B-Q8) was
|
| 18 |
converted to MLX format from [FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview](https://huggingface.co/FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview)
|
| 19 |
using mlx-lm version **0.21.4**.
|