---

base_model: DarwinAnim8or/Gemma4MoE-Lawd

library_name: peft

tags:

• llama-cpp
• gguf-my-lora
• roleplay
• sillytavern
• experimental

license: apache-2.0

language:

• en

---

Experimental RP tune for Gemma4 MoE (26b-a4b-it)

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.

Use with llama.cpp

# with cli
llama-cli -m base_model.gguf --lora Gemma4MoE-Lawd-f16.gguf (...other args)

# with server
llama-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.