ipetrukha/WizardCoder-33B-V1.1-4bit

The Model ipetrukha/WizardCoder-33B-V1.1-4bit was converted to MLX format from WizardLMTeam/WizardCoder-33B-V1.1 using mlx-lm version 0.16.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("ipetrukha/WizardCoder-33B-V1.1-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)