mlx-community/DeepSeek-V2-Lite-Chat-4bit-mlx

The Model mlx-community/DeepSeek-V2-Lite-Chat-4bit-mlx was converted to MLX format from deepseek-ai/DeepSeek-V2-Lite-Chat using mlx-lm version 0.16.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-V2-Lite-Chat-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)