Modelpublic

alexgusevski/saiga_yandexgpt_8b-q4-mlx

sourceHugging Faceotherupdated 9mo agoView on Hugging Face

0likes22downloads

Model Card

alexgusevski/saigayandexgpt8b-q4-mlx

This model alexgusevski/saiga_yandexgpt_8b-q4-mlx was converted to MLX format from IlyaGusev/saiga_yandexgpt_8b using mlx-lm version 0.30.2.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/saiga_yandexgpt_8b-q4-mlx")

prompt = "hello"

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

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