We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
update `-ngl` usage
remove --rope-scale
add gguf links
update 16k model loading
update llama-cpp when using 16k model
Update llamacpp_zh.md
update ppl w.r.t. llama-cpp-gguf
remove `-eps` term for gguf model
update to gguf version
update 13b results
update ppl and speed for llama.cpp
add eps for server command
Updated llamacpp_zh (markdown)
update server usage
fix sys prompt
init