HLWQ rebrand: title, tags, notice, self-links

docs: add HLWQ rebrand notice (cite Han et al. PolarQuant prior art)

fix: quant_method polar -> polarengine for vLLM compatibility

Upload config.json with huggingface_hub

Upload README.md with huggingface_hub

Update chat_template.jinja (#1)

Update tokenizer_config.json (#2)

Upload processor_config.json with huggingface_hub

Upload chat_template.jinja with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload polar_config.json with huggingface_hub

Upload README.md with huggingface_hub

Upload context.png with huggingface_hub

Upload family.png with huggingface_hub

Upload vram_breakdown.png with huggingface_hub

Upload compression.png with huggingface_hub

Add INT4 model (21 GB, direct load)

initial commit