st192011/llama3-midi-composer-gguf

SETUP MIDI TOKENIZER

midi_config = TokenizerConfig( pitch_range=(0, 127), num_velocities=127, beat_res={(0, 4): 32, (4, 12): 16}, use_tempos=True, num_tempos=32, tempo_range=(40, 250), use_programs=True, one_token_stream=True ) midi_tokenizer = REMI(midi_config)

llama3-midi-composer-gguf : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

• For text only LLMs: ./llama.cpp/llama-cli -hf st192011/llama3-midi-composer-gguf --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf st192011/llama3-midi-composer-gguf --jinja

Available Model files:

• llama-3-8b.Q4_K_M.gguf This was trained 2x faster with Unsloth