Instructions to use qgallouedec/DeepSeek-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qgallouedec/DeepSeek-R1 with Transformers:

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

pipe = pipeline("text-generation", model="qgallouedec/DeepSeek-R1", 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("qgallouedec/DeepSeek-R1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("qgallouedec/DeepSeek-R1", 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 qgallouedec/DeepSeek-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qgallouedec/DeepSeek-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qgallouedec/DeepSeek-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qgallouedec/DeepSeek-R1

SGLang

How to use qgallouedec/DeepSeek-R1 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 "qgallouedec/DeepSeek-R1" \
    --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": "qgallouedec/DeepSeek-R1",
		"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 "qgallouedec/DeepSeek-R1" \
        --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": "qgallouedec/DeepSeek-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qgallouedec/DeepSeek-R1 with Docker Model Runner:
```
docker model run hf.co/qgallouedec/DeepSeek-R1
```

Fix chat_template crash when assistant message omits the `content` key

by qgallouedec HF Staff - opened about 10 hours ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-1

qgallouedec

Owner about 10 hours ago

Fix `chat_template` to handle assistant messages without a `content` key

The problem

When an assistant message has tool_calls but no content key, the template crashes:

UndefinedError: 'dict object' has no attribute 'content'

Today this is rare because most callers pass content=None explicitly, which the template handles. But the upcoming transformers change https://github.com/huggingface/transformers/pull/45422 will strip content=None before rendering (treating None and absent as equivalent — which matches what the OpenAI API returns for tool-call-only messages). Once it ships, every tool-calling request through this template will fail.

Repro

Today (works):

from transformers import AutoTokenizer

tok = AutoTokenizer.from_pretrained("qgallouedec/DeepSeek-R1")
tok.apply_chat_template(
    [
        {"role": "user", "content": "What's the weather in Paris?"},
        {"role": "assistant", "content": None, "tool_calls": [{
            "type": "function",
            "function": {"name": "get_weather", "arguments": '{"city":"Paris"}'},
        }]},
    ],
    tokenize=False,
)
# renders correctly

After https://github.com/huggingface/transformers/pull/45422 (same call, same input — transformers strips content=None before rendering, so the template sees an absent key and crashes):

UndefinedError: 'dict object' has no attribute 'content'

You can reproduce the post-PR behavior today by simply omitting the content key.

The fix

One character: message['content'] is none → message.get('content') is none. The .get() returns None whether the key is absent or set to None, so both cases are handled identically.

Verified against 14 message-shape variants: 13 render bit-identically to the current template, 1 (the crashing case above) now renders correctly. No regressions.

Fix chat_template crash when assistant message omits the `content` key750095cf

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment

Fix chat_template crash when assistant message omits the `content` key

Fix chat_template to handle assistant messages without a content key

The problem

Repro

The fix

Fix `chat_template` to handle assistant messages without a `content` key