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

Libraries

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

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V2", 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-V2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V2", 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 deepseek-ai/DeepSeek-V2 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

This is by far the best model I have seen until now.

by ZeroWw - opened Jul 9, 2024

Discussion

ZeroWw

Jul 9, 2024

After testing many different models (gemini,gemma,llama and claude) I think this is the most promising model so far regarding reasoning and logic.
I wish to contact the people that created this model, because I have some ideas that could make AI progress by a factor of 2 or 4. Meaning: a smaller model could have the same reasoning capabilities.
I am serious, the problem is not just training (which can be done in a different way),
but is quite complex and I wish to brainstorm with the team and see if my ideas are right. If they are, and I have no reason to think otherwise, we could make a big breakthru in this field.

dipjeb

Nov 14, 2024

😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂😂

ZeroWw

Dec 2, 2024

This comment has been hidden

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