Instructions to use deepseek-ai/deepseek-coder-33b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/deepseek-coder-33b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/deepseek-coder-33b-instruct")
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-33b-instruct")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-33b-instruct")
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-coder-33b-instruct 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-33b-instruct"
# 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-33b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-coder-33b-instruct

SGLang

How to use deepseek-ai/deepseek-coder-33b-instruct 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-33b-instruct" \
    --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-33b-instruct",
		"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-33b-instruct" \
        --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-33b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/deepseek-coder-33b-instruct with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/deepseek-coder-33b-instruct
```

Why do we need the line trust_remote_code=True?

#23

by Rubiel1 - opened Feb 29, 2024

Discussion

Rubiel1

Feb 29, 2024

Hi,
What exactly are the implications of " trust_remote_code=True"?
Can we have a version without it?

luofuli

Mar 6, 2024

Yes, you can remove it.

The bellows are answers provided by deepseek coder 33B.

The trust_remote_code=True parameter in the from_pretrained method of the AutoTokenizer and AutoModelForCausalLM classes is used to indicate that the code being loaded from the remote repository should be trusted.

When you set trust_remote_code=True, the transformers library will execute the code from the remote repository, which can be a security risk if the code is not from a trusted source. This is because the code can execute arbitrary Python code, which can be used to perform malicious actions.

Therefore, it's generally recommended to set trust_remote_code=False to ensure that only trusted code is executed. This will prevent the execution of potentially harmful code.

If you want to use a version of the code without the trust_remote_code parameter, you can simply remove it from the from_pretrained method call. However, keep in mind that this will only work if the code is trusted. If the code is not trusted, it's recommended to use the trust_remote_code=False option to prevent the execution of potentially harmful code.

Rubiel1

Mar 6, 2024

Thanks!

Rubiel1 changed discussion status to closed Mar 6, 2024

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