README.zh.md: link KnowLine-4B-Gen4

README.md: link KnowLine-4B-Gen4

README.zh.md: link KnowLine-4B-Gen3

README.md: link KnowLine-4B-Gen3

Add knowline_engine.py (one-command Decision Index runs); --backend hf without accelerate

knowline_server.py: accept chat roles the template rejects; return 500 instead of dropping the connection

README.zh.md: link KnowLine-4B-Gen2, add DI 0.3 calibration

README.md: link KnowLine-4B-Gen2, add DI 0.3 calibration

Model card: README.md (English) and README.zh.md (Chinese)

INFERENCE.md and knowline_server.py header: describe the front end directly

Self-contained knowline_server.py front end; drop the llm2jev dependency

KnowLine-4B-Gen1: merged bf16 weights (E step 5650), tokenizer, serving files

initial commit