Views
No views yet
mlx_lm.convert (8-bit, group size 64).1pip install mlx-lm
2mlx_lm.generate --model layerx-labs/AMALIA-9B-0626-SFT-MLX-8bit --prompt "Explica o que é o Arquivo.pt."
3
4# or chat
5mlx_lm.chat --model layerx-labs/AMALIA-9B-0626-SFT-MLX-8bit1from mlx_lm import load, generate
2model, tokenizer = load("layerx-labs/AMALIA-9B-0626-SFT-MLX-8bit")
3prompt = tokenizer.apply_chat_template([{"role": "user", "content": "Explica o que é o Arquivo.pt."}], add_generation_prompt=True, tokenize=False)
4print(generate(model, tokenizer, prompt=prompt, max_tokens=256))