Instructions to use rl-research/DR-Tulu-8B-Step-1900 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rl-research/DR-Tulu-8B-Step-1900 with Transformers:

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

pipe = pipeline("text-generation", model="rl-research/DR-Tulu-8B-Step-1900")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rl-research/DR-Tulu-8B-Step-1900")
model = AutoModelForCausalLM.from_pretrained("rl-research/DR-Tulu-8B-Step-1900")
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 rl-research/DR-Tulu-8B-Step-1900 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rl-research/DR-Tulu-8B-Step-1900"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rl-research/DR-Tulu-8B-Step-1900",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rl-research/DR-Tulu-8B-Step-1900

SGLang

How to use rl-research/DR-Tulu-8B-Step-1900 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 "rl-research/DR-Tulu-8B-Step-1900" \
    --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": "rl-research/DR-Tulu-8B-Step-1900",
		"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 "rl-research/DR-Tulu-8B-Step-1900" \
        --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": "rl-research/DR-Tulu-8B-Step-1900",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rl-research/DR-Tulu-8B-Step-1900 with Docker Model Runner:
```
docker model run hf.co/rl-research/DR-Tulu-8B-Step-1900
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

For full information, go check out the Dr Tulu paper here. We have recently (24/11/2025) updated the model, please check the step_1000 branch for the previously released model.

DR Tulu-8B

This is the RL checkpoint of DR Tulu, an open deep research agent trained on top of rl-research/DR-Tulu-SFT-8B.

This model has undergone RL training on this dataset. For more details on DR Tulu please read our paper!

Inference and Usage

This model has been trained for tool-use using the dr-agent-lib framework. As such, running it out of the box with HuggingFace or vLLM will not work well!

See our github for more details on installation and how to run our model. Or check out our demo!

Evaluation Results

We provide evaluation instructions in our github.

Benchmark	SQAv2	HealthBench	ResearchQA	DeepResearch Bench	SimpleQA	2Wiki	WebWalker	Average
Qwen3-8B (naive rag)	40.4	16.5	56.1	33.3	52.6	18.9	8.8	32.4
Qwen3-8B (our search pipeline)	57.2	5.9	46.3	18.2	70.5	44.0	27.9	38.6
DR-Tulu-SFT-8B	72.3	38.1	68.5	39.0	75.5	66.5	31.9	56.0
DR-Tulu-8B (this model)	86.8	50.2	74.3	43.4	74.3	65.9	32.5	61.1

For more baselines, explanations of this table, and analysis of results, check out the Dr Tulu paper!

Intended uses & limitations

This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's Responsible Use Guidelines.

Training

The script used to train this model can be found here.

For hyperparameter details, check out the Dr Tulu paper.

Citation

@article{shao2025dr,
  title={DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research},
  author={Shao, Rulin and Asai, Akari and Shen, Shannon Zejiang and Ivison, Hamish and Kishore, Varsha and Zhuo, Jingming and Zhao, Xinran and Park, Molly and Finlayson, Samuel G and Sontag, David and others},
  journal={arXiv preprint arXiv:2511.19399},
  year={2025}
}

Downloads last month: 16

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for rl-research/DR-Tulu-8B-Step-1900

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

rl-research/DR-Tulu-SFT-8B

Finetuned

(3)

this model

Quantizations

2 models

Dataset used to train rl-research/DR-Tulu-8B-Step-1900

Paper for rl-research/DR-Tulu-8B-Step-1900

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Paper • 2511.19399 • Published Nov 24, 2025 • 63

rl-research
/

DR-Tulu-8B-Step-1900

DR Tulu-8B

Inference and Usage

Evaluation Results

Intended uses & limitations

Training

Links

Citation

Model tree for rl-research/DR-Tulu-8B-Step-1900

Dataset used to train rl-research/DR-Tulu-8B-Step-1900

Paper for rl-research/DR-Tulu-8B-Step-1900

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research