Image-Text-to-Text
Transformers
Safetensors
deepseek_v41
text-generation
deepseek
deepseek-v4.1
abliterated
uncensored
crack
multimodal
Mixture of Experts
fp8
8-bit precision
Instructions to use zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8
- SGLang
How to use zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8 with Docker Model Runner:
docker model run hf.co/zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8
Download model-00034-of-00048.safetensors from zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8: direct link, hf CLI and curl.
- Browser
- Download file 7.39 GB
-
https://huggingface.co/zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8/resolve/main/model-00034-of-00048.safetensors
- Command line
-
hf download hf://zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8/model-00034-of-00048.safetensors
-
curl -L -o model-00034-of-00048.safetensors https://huggingface.co/zugquants/DeepSeek-V4.1-Flash-UNCENSORED-FP8/resolve/main/model-00034-of-00048.safetensors
7.39 GB
- Xet hash:
- b787f2f9f68fef1c1011f9b2b636f17d758576a33476d75d172b14a1cdb70513
- Size of remote file:
- 7.39 GB
- SHA256:
- be409d2a8739134629475a9d20125a64283a42271f10a863e96475620702cb94
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.