README.md

metadata

base_model: google/gemma-2-9b-it
datasets:
  - princeton-nlp/gemma2-ultrafeedback-armorm
license: mit
tags:
  - alignment-handbook
  - generated_from_trainer
  - mlx
model-index:
  - name: princeton-nlp/gemma-2-9b-it-SimPO
    results: []

mlx-community/gemma-2-9b-it-SimPO

The Model mlx-community/gemma-2-9b-it-SimPO was converted to MLX format from princeton-nlp/gemma-2-9b-it-SimPO using mlx-lm version 0.18.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-2-9b-it-SimPO")
response = generate(model, tokenizer, prompt="hello", verbose=True)