Update README.md

README.md

@@ -12,7 +12,7 @@ language:
 
 # catalystsec/Seed-OSS-36B-Instruct-4bit-DWQ
 
-This model was quantized to 4-bit and optimized using DWQ (Dynamic Weight Quantization) with mlx-lm version **0.27.1**.
+This model was quantized to 4-bit using DWQ with mlx-lm version **0.27.1**, distilled from a BF16 teacher model.
 
 | Learning Rate | Total Loss | KL Loss | Activation Loss | Improvement |
 |---------------|------------|---------|-----------------|-------------|