Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: mlx
|
| 3 |
+
tags:
|
| 4 |
+
- mlx
|
| 5 |
+
- oq
|
| 6 |
+
- quantized
|
| 7 |
+
- mtp
|
| 8 |
+
base_model:
|
| 9 |
+
- tencent/Hy-MT2-7B
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Hy-MT2-7B-oQ6
|
| 13 |
+
|
| 14 |
+
This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.9) mixed-precision quantization.
|
| 15 |
+
|
| 16 |
+
## Quantization details
|
| 17 |
+
|
| 18 |
+
- **Model type**: hunyuan_v1_dense
|
| 19 |
+
- **Bits**: 6
|
| 20 |
+
- **Group size**: 64
|
| 21 |
+
- **Format**: MLX safetensors
|