This is Chinese-Llama-2-7b f16 ggml model running llama.cpp.You can run
./main -m Chinese-Llama-2-7b-f16-ggml.bin -p 'hello world'
from model see: https://huggingface.co/LinkSoul/Chinese-Llama-2-7b
- Downloads last month
- 0
Unable to determine this model's library. Check the
docs
.