metadata
license: gemma
library_name: transformers
tags:
- mlx
extra_gated_heading: Access CodeGemma on Hugging Face
extra_gated_prompt: >-
To access CodeGemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged-in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
pipeline_tag: text-generation
widget:
- text: >
<start_of_turn>user Write a Python function to calculate the nth fibonacci
number.<end_of_turn> <start_of_turn>model
inference:
parameters:
max_new_tokens: 200
license_link: https://ai.google.dev/gemma/terms
mlx-community/codegemma-7b-it-8bit
This model was converted to MLX format from google/codegemma-7b-it
using mlx-lm version 0.8.0.
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("mlx-community/codegemma-7b-it-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)