README.md

metadata

datasets:
  - openbmb/UltraFeedback
language:
  - en
license: gemma
pipeline_tag: text-generation
tags:
  - mlx

cyan2k/Gemma-2-9B-It-SPPO-Iter3-4bit-mlx

The Model cyan2k/Gemma-2-9B-It-SPPO-Iter3-4bit-mlx was converted to MLX format from UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3 using mlx-lm version 0.15.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cyan2k/Gemma-2-9B-It-SPPO-Iter3-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)