Upload README.md with huggingface_hub

README.md

@@ -56,12 +56,6 @@ output = model.generate(**inputs, max_new_tokens=128, do_sample=True,
 print(tokenizer.decode(output[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
 ```
 
-## Serving on HF Inference Endpoints
-
-This repo ships a `handler.py` that applies the chat template server-side —
-clients send plain text (or a messages list for multi-turn). Deploy with the
-Default container on a bf16-capable GPU (A10G or better).
-
 ## Limitations
 
 - Knowledge limited to the 2014 data vintage.