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

Libraries

How to use deepseek-ai/DeepSeek-V3.1-Base with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3.1-Base", 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("deepseek-ai/DeepSeek-V3.1-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3.1-Base", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V3.1-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V3.1-Base"
# 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-V3.1-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V3.1-Base

SGLang

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

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

msr2000 commited on Aug 26, 2025

Commit

d3d4eaf

1 Parent(s): c230953

Update ue8m0 config & description

Browse files

Files changed (2) hide show

README.md +8 -1
config.json +2 -1

README.md CHANGED Viewed

@@ -52,7 +52,9 @@ DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinkin
 - **Higher thinking efficiency**: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.
-DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.
 ## Model Downloads
@@ -196,6 +198,11 @@ tokenizer.apply_chat_template(messages, tokenize=False, thinking=False, add_gene
 The model structure of DeepSeek-V3.1 is the same as DeepSeek-V3. Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running this model locally.
 ## License
 This repository and the model weights are licensed under the [MIT License](LICENSE).

 - **Higher thinking efficiency**: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.
+DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens.
+Additionally, DeepSeek-V3.1 is trained using the **UE8M0 FP8 scale data format on both model weights and activations** to ensure compatibility with microscaling data formats. Please refer to [DeepGEMM](https://github.com/deepseek-ai/DeepGEMM) for more details.
 ## Model Downloads
 The model structure of DeepSeek-V3.1 is the same as DeepSeek-V3. Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running this model locally.
+**Usage Recommendations:**
+1. **The `mlp.gate.e_score_correction_bias `parameters should be loaded and computed in FP32 precision.**
+2. **Ensure that FP8 model weights and activations are formatted using the UE8M0 scale format.**
 ## License
 This repository and the model weights are licensed under the [MIT License](LICENSE).

config.json CHANGED Viewed

@@ -41,7 +41,8 @@
     "weight_block_size": [
       128,
       128
-    ]
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {

     "weight_block_size": [
       128,
       128
+    ],
+    "scale_fmt": "ue8m0"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {