youmego

looking forward to support MoE deepseek v2 total:236B active:21B +--------------------------+---------------+---------------------+-----------------+-------------------+ | Model | #Total Params | #Activated Params | Context Length | Download | +--------------------------+---------------+---------------------+-----------------+-------------------+ | DeepSeek-V2 | 236B |...

you can download deepseek-r1 8-bit form https://huggingface.co/meituan/DeepSeek-R1-Block-INT8