Update serving instructions: reflect 256k limit, mamba caching, and 16G swap space

Upload tokenizer.json.bak with huggingface_hub

Upload model-00001-of-00003.safetensors with huggingface_hub

Upload config.json.bak with huggingface_hub

Upload config.json with huggingface_hub

Upload tokenizer_config.json.bak with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload model-00003-of-00003.safetensors with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload README.md with huggingface_hub

Upload video_preprocessor_config.json with huggingface_hub

Upload model-00002-of-00003.safetensors with huggingface_hub

Upload model-00001-of-00003.safetensors with huggingface_hub

Upload chat_template.jinja with huggingface_hub

Upload preprocessor_config.json with huggingface_hub

Upload hf_quant_config.json with huggingface_hub

Upload processor_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload model-00003-of-00003.safetensors with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload model.safetensors.index.json with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload README.md with huggingface_hub

initial commit