Instructions to use unsloth/DeepSeek-V3.1-Terminus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/DeepSeek-V3.1-Terminus with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="unsloth/DeepSeek-V3.1-Terminus", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/DeepSeek-V3.1-Terminus", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-V3.1-Terminus", trust_remote_code=True)
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/DeepSeek-V3.1-Terminus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/DeepSeek-V3.1-Terminus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/DeepSeek-V3.1-Terminus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/DeepSeek-V3.1-Terminus

SGLang

How to use unsloth/DeepSeek-V3.1-Terminus 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 "unsloth/DeepSeek-V3.1-Terminus" \
    --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": "unsloth/DeepSeek-V3.1-Terminus",
		"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 "unsloth/DeepSeek-V3.1-Terminus" \
        --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": "unsloth/DeepSeek-V3.1-Terminus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use unsloth/DeepSeek-V3.1-Terminus with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-V3.1-Terminus
```

DeepSeek-V3.1-Terminus

Introduction

This update maintains the model's original capabilities while addressing issues reported by users, including:

Language consistency: Reducing instances of mixed Chinese-English text and occasional abnormal characters;
Agent capabilities: Further optimizing the performance of the Code Agent and Search Agent.

Benchmark	DeepSeek-V3.1	DeepSeek-V3.1-Terminus
Reasoning Mode w/o Tool Use
MMLU-Pro	84.8	85.0
GPQA-Diamond	80.1	80.7
Humanity's Last Exam	15.9	21.7
LiveCodeBench	74.8	74.9
Codeforces	2091	2046
Aider-Polyglot	76.3	76.1
Agentic Tool Use
BrowseComp	30.0	38.5
BrowseComp-zh	49.2	45.0
SimpleQA	93.4	96.8
SWE Verified	66.0	68.4
SWE-bench Multilingual	54.5	57.8
Terminal-bench	31.3	36.7

The template and tool-set of search agent have been updated, which is shown in assets/search_tool_trajectory.html.

How to Run Locally

The model structure of DeepSeek-V3.1-Terminus is the same as DeepSeek-V3. Please visit DeepSeek-V3 repo for more information about running this model locally.

For the model's chat template other than search agent, please refer to the DeepSeek-V3.1 repo.

Here we also provide an updated inference demo code in the inference folder to help the community get started with running our model and understand the details of model architecture.

NOTE: In the current model checkpoint, the parameters of self_attn.o_proj do not conform to the UE8M0 FP8 scale data format. This is a known issue and will be corrected in future model releases.

License

This repository and the model weights are licensed under the MIT License.

Citation

@misc{deepseekai2024deepseekv3technicalreport,
      title={DeepSeek-V3 Technical Report}, 
      author={DeepSeek-AI},
      year={2024},
      eprint={2412.19437},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.19437}, 
}