README.md

metadata

thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
license: apache-2.0
language:
  - ja
  - en
tags:
  - qwen2
  - conversational
  - mlx
base_model: rinna/qwq-bakeneko-32b
base_model_relation: merge
pipeline_tag: text-generation
library_name: transformers

mlx-community/qwq-bakeneko-32b-4bit

The Model mlx-community/qwq-bakeneko-32b-4bit was converted to MLX format from rinna/qwq-bakeneko-32b using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/qwq-bakeneko-32b-4bit")

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)