This model was converted to MLX format from
codellama/CodeLlama-7b-Python-hf.
Refer to the
original model card for more details on the model.
1from mlx_lm import load, generate
2
3model, tokenizer = load("mlx-community/CodeLlama-7b-Python-4bit")
4response = generate(model, tokenizer, prompt="<s>[INST] <<SYS>> You are a helpful, respectful, and honest assistant. Always do... If you are unsure about an answer, truthfully say \"I don't know\" <</SYS>> What's the meaning of life [/INST]", verbose=True)
