connect_ai_moonmoon_brain-v3 : GGUF

• For text only LLMs: llama-cli -hf moonglegle/connect_ai_moonmoon_brain-v3 --jinja
• For multimodal models: llama-mtmd-cli -hf moonglegle/connect_ai_moonmoon_brain-v3 --jinja

Available Model files:

• gemma-2b-it.Q4_K_M.gguf

Note

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