tinyinfer playground

A tiny GPT-2 inference engine in NumPy.

Prompt0 chars

max temp top-k seed

output–
tokens–

API

curl -sN https://tinyinfer.himanshu.co/api/generate \
  -H 'content-type: application/json' \
  -d '{"prompt": "The capital of France is",
       "max_new_tokens": 64, "temperature": 0.8}'