metadata

library_name: mlx
license: gemma
widget:
  - messages:
      - role: user
        content: How does the brain work?
inference:
  parameters:
    max_new_tokens: 200
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
  To access Gemma 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
base_model: google/gemma-1.1-2b-it
tags:
  - mlx
pipeline_tag: text-generation

mlx-community/gemma-1.1-2b-it-bf16

This model mlx-community/gemma-1.1-2b-it-bf16 was converted to MLX format from google/gemma-1.1-2b-it using mlx-lm version 0.26.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-1.1-2b-it-bf16")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)