Update model card for petergilani/MiniMax-M2.5-mix3-6bit

README.md

@@ -32,14 +32,12 @@ Mixed precision quantized version of MiniMax M2.5 using mlx-lm with `--quant-pre
 | Property | Value |
 |----------|-------|
 | **Base Model** | [MiniMaxAI/MiniMax-M2.5](https://huggingface.co/MiniMaxAI/MiniMax-M2.5) |
-| **Quantization Method** | mlx-lm v0.30.7 with `--quant-predicate mixed_3_6` |
+| **Quantization** | mlx-lm v0.30.7 with `--quant-predicate mixed_3_6` |
 | **Library** | [mlx-lm](https://github.com/huggingface/mlx-lm) |
 | **License** | modified-mit |
 
 ## Inference Parameters
 
-Recommended generation parameters (from original model):
-
 | Parameter | Value |
 |-----------|-------|
 | **temperature** | 1.0 |