dylama : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf chorgle/dylama --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf chorgle/dylama --jinja

Available Model files:

• Meta-Llama-3.1-8B-Instruct-abliterated.Q4_K_M.gguf

Note

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