Instructions to use sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir deepseek-coder-33b-instruct-mlx-4Bit sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
metadata
license: other
license_name: deepseek
license_link: LICENSE
tags:
- mlx
base_model: deepseek-ai/deepseek-coder-33b-instruct
sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit
The Model sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit was converted to MLX format from deepseek-ai/deepseek-coder-33b-instruct using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit")
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)