Modelpublic

mlx-community/Baichuan-M1-14B-Instruct-4bit-ft

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes50downloads

Model Card

mlx-community/Baichuan-M1-14B-Instruct-4bit

The model's tokenizer has been converted to a fast tokenizer (ft). Since swift-transformers does not currently support custom tokenizers, it has been switched to the supported Fast Tokenizer. If you are using mlx-swift, it is recommended to use this model.

This model mlx-community/Baichuan-M1-14B-Instruct-4bit-ft was converted to MLX format from baichuan-inc/Baichuan-M1-14B-Instruct using mlx-lm version 0.23.2.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Baichuan-M1-14B-Instruct-4bit-ft")

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)