README.md

metadata

license: other
license_name: deepseek
license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
library_name: transformers
tags:
  - mlx
base_model: deepseek-ai/DeepSeek-V2.5-1210

dong-99/DeepSeek-V2.5-1210-mlx-8Bit

The Model dong-99/DeepSeek-V2.5-1210-mlx-8Bit was converted to MLX format from deepseek-ai/DeepSeek-V2.5-1210 using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("dong-99/DeepSeek-V2.5-1210-mlx-8Bit")

prompt="hello"

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

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