Instructions to use deepseek-ai/DeepSeek-V2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V2.5 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V2.5", 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-V2.5", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V2.5", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V2.5"
# 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-V2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V2.5

SGLang

How to use deepseek-ai/DeepSeek-V2.5 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-V2.5" \
    --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-V2.5",
		"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-V2.5" \
        --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-V2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V2.5 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V2.5
```

012jaus commited on Sep 19, 2024

Commit

a161128

verified ·

1 Parent(s): 24b08cb

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -2,6 +2,11 @@
 license: other
 license_name: deepseek
 license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
 ---
 <!-- markdownlint-disable first-line-h1 -->
@@ -270,4 +275,4 @@ This code repository is licensed under the MIT License. The use of DeepSeek-V2 B
 ```
 ## 5. Contact
-If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com).

 license: other
 license_name: deepseek
 license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
+base_model:
+- GPT4All-Community/Meta-Llama-3.1-8B-Instruct-128k-GGUF
+- microsoft/Phi-3.5-MoE-instruct
+- black-forest-labs/FLUX.1-dev
+- Deniskin/gpt3_medium
 ---
 <!-- markdownlint-disable first-line-h1 -->
 ```
 ## 5. Contact
+If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com).