# Hugging Face Inference API Configuration # ============================================ # Mode: API (recommended) or Local # ============================================ # Use HF Inference API (true) or load model locally (false) HF_USE_API=true # HF API token (get it from https://huggingface.co/settings/tokens) # Required if HF_USE_API=true HF_API_TOKEN=hf_xxxxxxxxxxxxxxxxxxxxx # ============================================ # Model Configuration # ============================================ # Model to use (any Hugging Face model ID) HF_MODEL_NAME=distilbert-base-uncased-finetuned-sst-2-english # Task type (text-classification, text-generation, summarization, etc.) HF_TASK=text-classification # ============================================ # Server Configuration # ============================================ HF_HOST=0.0.0.0 HF_PORT=8000 # ============================================ # Local Mode Only (ignored if HF_USE_API=true) # ============================================ # Device (cpu, cuda, cuda:0, etc.) HF_DEVICE=cpu # Maximum batch size for inference HF_MAX_BATCH_SIZE=32