huihui-ai/MiMo-7B-SFT-abliterated
#1398
by
AIgotahole
- opened
ERROR:hf-to-gguf:Model MiMoForCausalLM is not supported
Help...
It unfortunately is indeed not supported by llama.cpp: https://github.com/ggml-org/llama.cpp/issues/13218
I recommend you instead run it using vLLM which does support it. You can even use bitsandbytes to load it in 4-bit.
Oh I see it now. MiMo-VL-7B was actually based on Qwen2_5_VL as why it is supported. I think I confused it with MiMo-7B. :P