Trained for 4 epochs on restraint training, just a test run. Feel free to use it if you want, if you get anything fun let me know in the community tab.
I used temp=1, top_p=0.9 with loramult=0.7 in Kobold / SillyTavern chat completion.
1# with cli
2llama-cli -m base_model.gguf --lora Gemma4MoE-Lawd-f16.gguf (...other args)
3
4# with server
5llama-server -m base_model.gguf --lora Gemma4MoE-Lawd-f16.gguf (...other args)
To know more about LoRA usage with llama.cpp server, refer to the
llama.cpp server documentation.
