mukunds15/gemma_trial

This model was converted to MLX format from mlx-community/gemma-1.1-7b-it-4bit using mlx-lm version 0.11.0. 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("mukunds15/gemma_trial")
response = generate(model, tokenizer, prompt="hello", verbose=True)