Instructions to use deepseek-ai/DeepSeek-V4-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V4-Flash with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V4-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Flash")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Flash")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-V4-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V4-Flash"
# 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-V4-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash

SGLang

How to use deepseek-ai/DeepSeek-V4-Flash 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-V4-Flash" \
    --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-V4-Flash",
		"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-V4-Flash" \
        --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-V4-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V4-Flash with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash
```

[适配请求] 建议 API 兼容 OpenAI 新规范中的 developer 角色（It is recommended that the API be compatible with the developer role in the new OpenAI specification

#19

by xusu616 - opened 12 days ago

Discussion

xusu616

12 days ago

•

edited 12 days ago

目前在使用 Android Studio (版本 panda1 patch) ~~（算近的稳定版本，新版太多bug了）~~ 时接了 DeepSeek API 时，请求会直接报错返回 400

Please try again later.
Error: com.openai.errors.BadRequestException: 400: Failed to deserialize the JSON body into the target type: messages[0].role: unknown variant developer, expected one of system, user, assistant, tool, latest_reminder at line 1 column 2047

OpenAI 最近更新了 API 规范，引入了 developer 角色来取代原本的 system 角色（用于设置模型行为指令）。目前很多基于 Jetpack Compose 开发的最新工具链已经默认发送 role: "developer" 格式的 JSON 请求包

请求：

DeepSeek API 后端目前似乎只接受 system, user, assistant 这三个变体。建议后端进行兼容性适配：

自动映射：在收到 role: "developer" 时，后端自动将其识别并处理为 system 角色。

xusu616 changed discussion title from 建议 API 兼容 OpenAI 新规范中的 developer 角色（It is recommended that the API be compatible with the developer role in the new OpenAI specification to [适配请求] 建议 API 兼容 OpenAI 新规范中的 developer 角色（It is recommended that the API be compatible with the developer role in the new OpenAI specification 12 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

[适配请求] 建议 API 兼容 OpenAI 新规范中的 developer 角色 （It is recommended that the API be compatible with the developer role in the new OpenAI specification

[适配请求] 建议 API 兼容 OpenAI 新规范中的 developer 角色（It is recommended that the API be compatible with the developer role in the new OpenAI specification