smarthome_functiongemma_finetune : GGUF

• For text only LLMs: llama-cli -hf YouziMa/smarthome_functiongemma_finetune --jinja
• For multimodal models: llama-mtmd-cli -hf YouziMa/smarthome_functiongemma_finetune --jinja

Available Model files:

• smarthome_functiongemma_lora.Q8_0.gguf

Note

The model's BOS token behavior was adjusted for GGUF compatibility. This was trained 2x faster with Unsloth