OpenThinker-7B

Instructions to use open-thoughts/OpenThinker-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-thoughts/OpenThinker-7B with Transformers:

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

pipe = pipeline("text-generation", model="open-thoughts/OpenThinker-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-thoughts/OpenThinker-7B")
model = AutoModelForCausalLM.from_pretrained("open-thoughts/OpenThinker-7B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use open-thoughts/OpenThinker-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-thoughts/OpenThinker-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "open-thoughts/OpenThinker-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/open-thoughts/OpenThinker-7B

SGLang

How to use open-thoughts/OpenThinker-7B 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 "open-thoughts/OpenThinker-7B" \
    --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": "open-thoughts/OpenThinker-7B",
		"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 "open-thoughts/OpenThinker-7B" \
        --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": "open-thoughts/OpenThinker-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-thoughts/OpenThinker-7B with Docker Model Runner:
```
docker model run hf.co/open-thoughts/OpenThinker-7B
```

Thinking prompt not included in template

by Doctor-Chad-PhD - opened Feb 21, 2025

Discussion

Doctor-Chad-PhD

Feb 21, 2025

Hi,

I was just wondering if the thinking prompt could be added to the jinja template in tokenizer_config.json?

On line 198 it's just the regular Qwen template, so when converting this model to quants or using it with any inference software other than the official repo, it fails to start reasoning.

https://huggingface.co/open-thoughts/OpenThinker-7B/blob/5a931fd3fa8618acda2da8eaec4a3f10ee009739/tokenizer_config.json#L198

I believe it's also missing from the added_tokens.json file.

The only way to invoke it right now is to manually add <|begin_of_thought|> to the end of a prompt.

Thank you.

ryanmarten

OpenThoughts org Feb 22, 2025

Could you please provide a bit more detail on how you are running the model?

With this chat template (and without the thinking prompt) the model is still producing reasoning. I also checked the default 7B quant on Ollama and I wasn't running into any issues there.

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