requirements.txt

# TinyBard — Micro Text Adventure Generator
# Python 3.10+
#
# Inference is via the Hugging Face Inference API (no local GGUF,
# no llama-cpp-python compile). Cooldown is enforced in
# `shared/inference_client.py` to protect your credit budget.
#
# Set these Space secrets/variables to configure:
#   HF_TOKEN              — your HF token (anonymous works for many small models)
#   INFERENCE_MODEL       — model id (default: Qwen/Qwen2.5-1.5B-Instruct)
#   TINYBARD_COOLDOWN_SECONDS — gap between inference calls (default 6)
#   INFERENCE_PROVIDER    — "hf-inference" (default, free serverless) or paid
#   INFERENCE_MAX_TOKENS  — per-call token cap (default 220)

gradio>=5.0
fastapi>=0.110
huggingface_hub>=0.20
uvicorn[standard]>=0.27