README.md

metadata

language:
  - multilingual
license: other
license_name: kwaipilot-license
license_link: LICENSE
library_name: mlx
pipeline_tag: text-generation
tags:
  - mlx
base_model: Kwaipilot/KwaiCoder-AutoThink-preview

mlx-community/KwaiCoder-AutoThink-preview-6bit

This model mlx-community/KwaiCoder-AutoThink-preview-6bit was converted to MLX format from Kwaipilot/KwaiCoder-AutoThink-preview using mlx-lm version 0.25.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/KwaiCoder-AutoThink-preview-6bit")

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)