ccczxxa/quick-encoder-v2

Code Generation

Code completion with CodeGen-350M-mono. Lightweight model serving with dynamic batching.

Features

• —Built-in tokenizer with padding and truncation
• —Automatic model caching and versioning
• —Model quantization support (INT8/FP16)

API

POST /predict      — Run model inference on input
GET  /model/info   — Model metadata and config