metadata
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
inference: false
heimberglee/XVERSE-13B-256K-Q4_K_M-GGUF
This model was converted to GGUF format from xverse/XVERSE-13B-256K
using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Use with llama.cpp
Install llama.cpp through brew.
brew install ggerganov/ggerganov/llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo heimberglee/XVERSE-13B-256K-Q4_K_M-GGUF --model xverse-13b-256k.Q4_K_M.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo heimberglee/XVERSE-13B-256K-Q4_K_M-GGUF --model xverse-13b-256k.Q4_K_M.gguf -c 2048
Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m xverse-13b-256k.Q4_K_M.gguf -n 128