Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,35 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: other
|
| 3 |
-
license_name: qwen
|
| 4 |
-
license_link: LICENSE
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: qwen
|
| 4 |
+
license_link: https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct/blob/main/LICENSE
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
base_model: Qwen/Qwen2.5-Math-72B-Instruct
|
| 7 |
+
tags:
|
| 8 |
+
- math
|
| 9 |
+
- chat
|
| 10 |
+
- 6bit
|
| 11 |
+
language:
|
| 12 |
+
- en
|
| 13 |
+
- zh
|
| 14 |
+
library_name: mlx
|
| 15 |
+
---
|
| 16 |
+
# Qwen2.5 Math 72B Instruct 6-bit MLX
|
| 17 |
+
MLX version of **Qwen2.5 Math 72B Instruct**
|
| 18 |
+
|
| 19 |
+
This model was converted to MLX format from [`https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct`]() using mlx-lm version **0.22.5**.
|
| 20 |
+
|
| 21 |
+
## Model Details
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
For more details, please refer to [blog post](https://qwenlm.github.io/blog/qwen2.5-math/) and [GitHub repo](https://github.com/QwenLM/Qwen2.5-Math).
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
## Use with mlx
|
| 28 |
+
|
| 29 |
+
```bash
|
| 30 |
+
pip install -U mlx-lm
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
```bash
|
| 34 |
+
python -m mlx_lm.generate --model TheCluster/Qwen2.5-Math-72B-Instruct-mlx-6bit --max-tokens 1024 --temperature 0.5 --prompt "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."
|
| 35 |
+
```
|