Text Generation
Transformers
Safetensors
deepseek_v4
cybersecurity
ctf
autonomous-agent
mixture-of-experts
long-context
reinforcement-learning
grpo
lora
security-research
fp8
Instructions to use a15846/DeepSeek-v4-Fable with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use a15846/DeepSeek-v4-Fable with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="a15846/DeepSeek-v4-Fable")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("a15846/DeepSeek-v4-Fable") model = AutoModelForCausalLM.from_pretrained("a15846/DeepSeek-v4-Fable", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use a15846/DeepSeek-v4-Fable with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "a15846/DeepSeek-v4-Fable" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "a15846/DeepSeek-v4-Fable", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/a15846/DeepSeek-v4-Fable
- SGLang
How to use a15846/DeepSeek-v4-Fable 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 "a15846/DeepSeek-v4-Fable" \ --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": "a15846/DeepSeek-v4-Fable", "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 "a15846/DeepSeek-v4-Fable" \ --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": "a15846/DeepSeek-v4-Fable", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use a15846/DeepSeek-v4-Fable with Docker Model Runner:
docker model run hf.co/a15846/DeepSeek-v4-Fable
Download banner.png from a15846/DeepSeek-v4-Fable: direct link, hf CLI and curl.
- Browser
- Download file 787 kB
-
https://huggingface.co/a15846/DeepSeek-v4-Fable/resolve/main/banner.png
- Command line
-
hf download hf://a15846/DeepSeek-v4-Fable/banner.png
-
curl -L -o banner.png https://huggingface.co/a15846/DeepSeek-v4-Fable/resolve/main/banner.png
787 kB

- Xet hash:
- bf8e55f8cc2f754d70fcd1c7180f1e8e229ca4d15bb5c721eb3d4b87df602f46
- Size of remote file:
- 787 kB
- SHA256:
- 84926fe2279e549d3704c5928d45f1c3179cef59c0f5e912d7b96c874a1a8663
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.