Text Generation
MLX
Safetensors
English
Chinese
deepseek_v4
deepseek
deepseek-v4
Mixture of Experts
abliterated
uncensored
crack
jang
long-context
reasoning
Instructions to use dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK" --prompt "Once upon a time"
- Atomic Chat
Download model-00008-of-00102.safetensors from dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK: direct link, hf CLI and curl.
- Browser
- Download file 1 GB
-
https://huggingface.co/dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK/resolve/main/model-00008-of-00102.safetensors
- Command line
-
hf download hf://dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK/model-00008-of-00102.safetensors
-
curl -L -o model-00008-of-00102.safetensors https://huggingface.co/dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK/resolve/main/model-00008-of-00102.safetensors
1 GB
- Xet hash:
- a1b9379dcedb460b89315eda8b37ec711425f7f06fea3aaf1a72bcd55ac59571
- Size of remote file:
- 1 GB
- SHA256:
- 5b0e0f471b430b6791f2964ed038b99b89ba5653b76a5e6fc56687bd174a6bd0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.