mlx-community/CodeLlama-34b-Instruct-hf-4bit

This model was converted to MLX format from codellama/CodeLlama-34b-Instruct-hf. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/CodeLlama-34b-Instruct-hf-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)