search

RWKV / rwkv.cpp

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
MIT License
1.42k stars 98 forks source link

Add support for loading RWKV v6 GGUF files #180

Open MollySophia opened 2 months ago

MollySophia commented 2 months ago

GGUF files are converted using llama.cpp convert_hf_to_gguf.py script (https://github.com/ggerganov/llama.cpp/pull/8980)