Instructions to use mlx-community/DeepSeek-R1-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/DeepSeek-R1-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir DeepSeek-R1-4bit mlx-community/DeepSeek-R1-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
I am unable to load this model.
#1
by arjunsama - opened
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/DeepSeek-R1-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
//using this code.
the above error . could this be because of disk space issues?
Any help is appreciated.