README.md

metadata

license: gemma
datasets:
  - openbmb/UltraFeedback
language:
  - en
pipeline_tag: text-generation
library_name: mlx
tags:
  - mlx
base_model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3

mlx-community/Gemma-2-9B-It-SPPO-Iter3-8bit

This model mlx-community/Gemma-2-9B-It-SPPO-Iter3-8bit was converted to MLX format from UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3 using mlx-lm version 0.26.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Gemma-2-9B-It-SPPO-Iter3-8bit")

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)