Text Generation
Transformers
Safetensors
deepseek_v3
conversational
custom_code
Eval Results
text-generation-inference
fp8
Instructions to use deepseek-ai/DeepSeek-V3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepseek-ai/DeepSeek-V3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V3", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3", trust_remote_code=True, device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use deepseek-ai/DeepSeek-V3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepseek-ai/DeepSeek-V3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/deepseek-ai/DeepSeek-V3
- SGLang
How to use deepseek-ai/DeepSeek-V3 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 "deepseek-ai/DeepSeek-V3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "deepseek-ai/DeepSeek-V3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use deepseek-ai/DeepSeek-V3 with Docker Model Runner:
docker model run hf.co/deepseek-ai/DeepSeek-V3
Commit History
-
remove reference to deprecated transformers code
Verified signaturein latest transformers, `is_torch_greater_or_equal_than_1_13` has been removed.bf02b98
-
add `transformers` library name (enable inference) (#66)
Verified signature- add `transformers` library name (enable inference) (e1a21ff19a0aab2032b443759a77bfa5d10df223) Co-authored-by: Caleb Fahlgren <cfahlgren1@users.noreply.huggingface.co>1d044fd -
Update README_WEIGHTS.md
Verified signature0cf1748 -
fix the calculation of act params
Verified signature108e1e0
-
Update README.md
Verified signatureadd citation format to the arxiv-version paper4c1f24c
-
Fix fp8_cast_bf16.py: https://github.com/deepseek-ai/DeepSeek-V3/commit/8f1c9488b53068992f9525fab03b1868e6f7c8c1
9672b38 -
Update README.md with vLLM Support (#8)
Verified signature- Update README.md with vLLM Support (87663416be779d980e4aa102edc328b85d7802f6) Co-authored-by: Simon Mo <simon-mo@users.noreply.huggingface.co>9ffbf9c
-
Release DeepSeek-V3
dd31960 -
Add files using upload-large-folder tool
Verified signature52af7fb -
Add files using upload-large-folder tool
Verified signature0d9fddb -
Add files using upload-large-folder tool
Verified signature8a89bc2 -
Add files using upload-large-folder tool
Verified signaturee24a9e9 -
Add files using upload-large-folder tool
Verified signaturebd0dd75 -
Add files using upload-large-folder tool
Verified signatureb734e5d -
Add files using upload-large-folder tool
Verified signaturea5aa653 -
Add files using upload-large-folder tool
Verified signature4b992ad -
Add files using upload-large-folder tool
Verified signatured990f04
-
initial commit
Verified signature198edc6