metadata
license: other
license_name: deepseek
license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
tags:
- mlx
base_model: deepseek-ai/DeepSeek-V2-Chat
Wwayu/DeepSeek-V2-Chat-mlx-2Bit
The Model Wwayu/DeepSeek-V2-Chat-mlx-2Bit was converted to MLX format from deepseek-ai/DeepSeek-V2-Chat using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Wwayu/DeepSeek-V2-Chat-mlx-2Bit")
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)