tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit

1---2language:3- multilingual4license: other5license_name: kwaipilot-license6license_link: LICENSE7library_name: transformers8tags:9- mlx10base_model: Kwaipilot/KwaiCoder-AutoThink-preview11---12 13# tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit14 15The Model [tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit](https://huggingface.co/tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit) was converted to MLX format from [Kwaipilot/KwaiCoder-AutoThink-preview](https://huggingface.co/Kwaipilot/KwaiCoder-AutoThink-preview) using mlx-lm version **0.22.3**.16 17## Use with mlx18 19```bash20pip install mlx-lm21```22 23```python24from mlx_lm import load, generate25 26model, tokenizer = load("tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit")27 28prompt="hello"29 30if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:31    messages = [{"role": "user", "content": prompt}]32    prompt = tokenizer.apply_chat_template(33        messages, tokenize=False, add_generation_prompt=True34    )35 36response = generate(model, tokenizer, prompt=prompt, verbose=True)37```38