macmacmacmac
/

qwen-webgpu-lora

Text Generation

Model card Files Files and versions

qwen-webgpu-lora / README.md

Commit History

Model card: add context window & prefill sizes; base_model = VibeThinker-3B (128K)

3ec6064

macmacmacmac commited on 4 days ago

Emberglass model card: in-browser WebGPU Qwen2.5-3B + runtime LoRA hot-swap

175cd4d

macmacmacmac commited on 4 days ago