Add files using upload-large-folder tool

README.md

@@ -21,6 +21,8 @@ This model was quantized to 3-bit using DWQ with mlx-lm version **0.28.4**.
 | Relative KL reduction     | ≈40 %                         |
 | Tokens processed          | ≈1.09 M                        |
 
+<img src="minimax_3e-7.png" width="600" alt="Training loss curve">
+
 ## Use with mlx
 
 ```bash