kasys/llm-jp-4-8b-thinking-q4f16_1-MLC

Recompile with context_window_size=16384 (llm-jp-4-8b-thinking-q4f16_1-webgpu.wasm)

Recompile with context_window_size=16384 (mlc-chat-config.json)

Rewrite model card in English

Add model card

Add MLC q4f16_1 weights + WebGPU wasm for WebLLM (llm-jp-4-8b-thinking, Harmony)

initial commit