Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ pipeline_tag: text-generation
|
|
| 17 |
|
| 18 |
# MiniMax-M2.5 3-bit MLX
|
| 19 |
|
|
|
|
|
|
|
| 20 |
This is a 3-bit quantized [MLX](https://github.com/ml-explore/mlx) version of [MiniMaxAI/MiniMax-M2.5](https://huggingface.co/MiniMaxAI/MiniMax-M2.5), converted using [mlx-lm](https://github.com/ml-explore/mlx-lm) v0.30.7.
|
| 21 |
|
| 22 |
MiniMax-M2.5 is a 229B parameter Mixture of Experts model (10B active parameters) that achieves 80.2% on SWE-Bench Verified and is SOTA in coding, agentic tool use, and search tasks.
|
|
|
|
| 17 |
|
| 18 |
# MiniMax-M2.5 3-bit MLX
|
| 19 |
|
| 20 |
+
**⚠️ UPLOAD IN PROGRESS -- model files still uploading, not yet ready for use.**
|
| 21 |
+
|
| 22 |
This is a 3-bit quantized [MLX](https://github.com/ml-explore/mlx) version of [MiniMaxAI/MiniMax-M2.5](https://huggingface.co/MiniMaxAI/MiniMax-M2.5), converted using [mlx-lm](https://github.com/ml-explore/mlx-lm) v0.30.7.
|
| 23 |
|
| 24 |
MiniMax-M2.5 is a 229B parameter Mixture of Experts model (10B active parameters) that achieves 80.2% on SWE-Bench Verified and is SOTA in coding, agentic tool use, and search tasks.
|