Instructions to use open-thoughts/OpenThinker3-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-thoughts/OpenThinker3-7B with Transformers:

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

pipe = pipeline("text-generation", model="open-thoughts/OpenThinker3-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-thoughts/OpenThinker3-7B")
model = AutoModelForCausalLM.from_pretrained("open-thoughts/OpenThinker3-7B")
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 Settings

vLLM

How to use open-thoughts/OpenThinker3-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-thoughts/OpenThinker3-7B"
# 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/OpenThinker3-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/open-thoughts/OpenThinker3-7B

SGLang

How to use open-thoughts/OpenThinker3-7B 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/OpenThinker3-7B" \
    --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/OpenThinker3-7B",
		"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/OpenThinker3-7B" \
        --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/OpenThinker3-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-thoughts/OpenThinker3-7B with Docker Model Runner:
```
docker model run hf.co/open-thoughts/OpenThinker3-7B
```

EtashGuha commited on Jun 5, 2025

Commit

af40378

verified ·

1 Parent(s): f2ac531

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -4

README.md CHANGED Viewed

@@ -29,9 +29,9 @@ State-of-the-art open-data 7B reasoning model. 🚀
 This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the
 [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset.
-It represents a notable improvement over our previous models, [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) and [OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B), and it outperforms several other strong reasoning 7B models such as [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) and [Llama-3.1-Nemotron-Nano-8B-v1](https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1), despite being trained only with SFT, without any RL.
-This time, we also release a paper! See our [paper](https://arxiv.org/abs/2506.04178) and [blog post](https://openthoughts.ai/blog/ot3) for more details. OpenThinker3-32B to follow! 👀
 # Evaluation Results
 The numbers reported in the table below are evaluated with our open-source tool [Evalchemy](https://github.com/mlfoundations/Evalchemy).
@@ -52,8 +52,8 @@ In the table below, we bold values in each column that are within 2 standard err
 This model was trained on the [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset.
-The key behind the strong model performance is our comprehensive data pipeline and 1000+ ablation experiments.
-This led to the creation of [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M), which consists of 850,000 math examples, 250,000 code examples, and 100,000 science examples.
 Reasoning traces are generated with QwQ-32B.
 See the [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset page or our [paper](https://arxiv.org/abs/2506.04178) for additional information.
@@ -81,6 +81,7 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 5.0
 ## Framework versions

 This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the
 [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset.
+It represents a notable improvement over our previous models, [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) and [OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B), and it outperforms several other strong reasoning 7B models such as [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) and [Llama-3.1-Nemotron-Nano-8B-v1](https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1), despite being trained only with SFT, without any RL.
+This time, we also released a paper! See our [paper](https://arxiv.org/abs/2506.04178) and [blog post](https://openthoughts.ai/blog/ot3) for more details. OpenThinker3-32B to follow! 👀
 # Evaluation Results
 The numbers reported in the table below are evaluated with our open-source tool [Evalchemy](https://github.com/mlfoundations/Evalchemy).
 This model was trained on the [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset.
+The key to the strong model performance is our comprehensive data pipeline and over 1,000+ ablation experiments.
+This led to the creation of [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M), which consists of 850,000 math questions, 250,000 code questions, and 100,000 science questions.
 Reasoning traces are generated with QwQ-32B.
 See the [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset page or our [paper](https://arxiv.org/abs/2506.04178) for additional information.
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 5.0
+- weight_decay: 0.0
 ## Framework versions