README.md

metadata

license: gemma
library_name: transformers
pipeline_tag: text-generation
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
tags:
  - conversational
  - mlx
  - mlx-my-repo
base_model: rtzr/ko-gemma-2-9b-it
language:
  - ko

KYUNGYONG/ko-gemma-2-9b-it-4bit

The Model KYUNGYONG/ko-gemma-2-9b-it-4bit was converted to MLX format from rtzr/ko-gemma-2-9b-it using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("KYUNGYONG/ko-gemma-2-9b-it-4bit")

prompt="hello"

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

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