Mini-MOEs - Mixture of Experts 2x, x4 and x8
Collection
Tiny but mighty. 1B, 1.1B, 2B (2x,x4,x8) MOE models. Suggest Q8 version, and review of original model page for template (!), usage & help.
•
31 items
•
Updated
•
4
This model was converted to GGUF format from Abhaykoul/HelpingAI-Lite-4x1b
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/HelpingAI-Lite-4x1b-Q8_0-GGUF --model helpingai-lite-4x1b.Q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo DavidAU/HelpingAI-Lite-4x1b-Q8_0-GGUF --model helpingai-lite-4x1b.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 helpingai-lite-4x1b.Q8_0.gguf -n 128