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

Libraries

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

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-Coder-V2-Lite-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-Coder-V2-Lite-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", 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 Settings

vLLM

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

Use Docker

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

SGLang

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

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

DeepSeek-Coder-V2-Lite-Base

Commit History

Update EvalEval source links to flat datastore

2a86cbf
verified

EvalEvalBot commited on 20 days ago

Add EvalEval community eval results

b151b6a
verified

EvalEvalBot commited on Jun 7

Add EvalEval community eval results

b090a50
verified

EvalEvalBot commited on Jun 5

Add EvalEval community eval results

8b0ecec
verified

EvalEvalBot commited on Jun 5

Update README.md

ea9b066
verified

guoday commited on Jul 3, 2024

Update modeling_deepseek.py

e5e79b9

mashirong commited on Jun 24, 2024

Update README.md

3da6ddf
verified

guoday commited on Jun 19, 2024

Update README.md

da8c524
verified

guoday commited on Jun 18, 2024

Update README.md

5d86791
verified

guoday commited on Jun 17, 2024

Update README.md

56ac6e9
verified

guoday commited on Jun 17, 2024

Create README.md

b409514
verified

guoday commited on Jun 16, 2024

Remove unused file

e346937

mashirong commited on Jun 14, 2024

Upload folder using huggingface_hub

5a3cf15
verified

msr2000 commited on Jun 14, 2024

initial commit

79474d7
verified

luofuli commited on Jun 14, 2024

Commit History

Update EvalEval source links to flat datastore 2a86cbf verified

Add EvalEval community eval results b151b6a verified

Add EvalEval community eval results b090a50 verified

Add EvalEval community eval results 8b0ecec verified

Update README.md ea9b066 verified

Update modeling_deepseek.py e5e79b9

Update README.md 3da6ddf verified

Update README.md da8c524 verified

Update README.md 5d86791 verified

Update README.md 56ac6e9 verified

Create README.md b409514 verified

Remove unused file e346937

Upload folder using huggingface_hub 5a3cf15 verified

initial commit 79474d7 verified