k2rks's picture
63f5ec41dcda4b77dd77f419c1f12de81a3fd0f72ccbe64d10d30eacdcc2b14c
982b5e2 verified
|
raw
history blame
706 Bytes
metadata
license: other
license_name: deepseek-license
license_link: LICENSE
tags:
  - mlx

mlx-community/DeepSeek-Coder-V2-Lite-Instruct-8bit

The Model mlx-community/DeepSeek-Coder-V2-Lite-Instruct-8bit was converted to MLX format from deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct using mlx-lm version 0.18.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-Coder-V2-Lite-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)