Gemma-3-270M / .env.example
unknown
Fixed the model optimzation speed
e06bc75
raw
history blame contribute delete
460 Bytes
# Hugging Face Authentication Token
# Get your token from: https://huggingface.co/settings/tokens
# Model Configuration
REPO_ID=unsloth/gemma-3-270m-it-GGUF
MODEL_FILENAME=gemma-3-270m-it-F16.gguf
# Server Configuration
PORT=7860
UVICORN_WORKERS=1
# Performance Tuning
MAX_WORKERS=2
MAX_CONCURRENT_REQUESTS=1
RATE_LIMIT_PER_MIN=60
REQUEST_TIMEOUT=120
# CORS Configuration
ALLOWED_ORIGINS=*
# Performance Optimizations
N_CTX=2048
N_THREADS=4
N_GPU_LAYERS=0