Upload README.md with huggingface_hub

README.md

@@ -68,7 +68,7 @@ print(generated_text)
 - **`fsd_div_type`** (str, default: "kl"): Type of divergence metric to use:
   - `"kl"`: KL divergence (D_KL(candidate || target)) - measures how much information is lost when using the candidate distribution to approximate the target
   - `"js"`: Jensen-Shannon divergence - a symmetric and bounded measure of distribution similarity
-  - `"draft_tokens"`: Absolute difference in draft token probabilities - simpler metric based on probability differences
+  - `"draft_tokens"`: Absolute difference between draft and target model probability of drafted token
 
 ### How It Works