Add Mixtral 8X7b to the models.md and run-llm.sh
alabulei1 opened this issue · comments
alabulei1 commented
Summary
I have tested Mixtral 8X7b on Jetson Orin. Both llama-chat.wasm and llama-api-server.wasm work. I think we can add this model to the models.md and run-llm.sh.
The model I used:
curl -LO https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/resolve/main/mixtral-8x7b-instruct-v0.1.Q5_K_M.gguf
The commandline to run this model via CLI:
wasmedge --dir .:. --nn-preload default:GGML:AUTO:mixtral-8x7b-instruct-v0.1.Q5_0.gguf llama-chat.wasm -p mistral-instruct
The command line to create an api server for this model:
wasmedge --dir .:. --nn-preload default:GGML:AUTO:mixtral-8x7b-instruct-v0.1.Q5_0.gguf llama-api-server.wasm -p mistral-instruct
Appendix
No response