Llama3 Models
Collection
Single quants of Lllama3 models - q6/q8.
•
33 items
•
Updated
This model was converted to GGUF format from shenzhi-wang/Llama3-8B-Chinese-Chat
using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Install llama.cpp through brew.
brew install ggerganov/ggerganov/llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo DavidAU/Llama3-8B-Chinese-Chat-Q8_0-GGUF --model llama3-8b-chinese-chat.Q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo DavidAU/Llama3-8B-Chinese-Chat-Q8_0-GGUF --model llama3-8b-chinese-chat.Q8_0.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 llama3-8b-chinese-chat.Q8_0.gguf -n 128
Base model
meta-llama/Meta-Llama-3-8B-Instruct