Instructions to use hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE with Transformers:

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

pipe = pipeline("text-generation", model="hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE")
model = AutoModelForMultimodalLM.from_pretrained("hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE")
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 hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE

SGLang

How to use hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE 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 "hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE" \
    --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": "hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE",
		"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 "hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE" \
        --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": "hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE with Docker Model Runner:
```
docker model run hf.co/hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

For full information, go check out the RLVE paper here.

Nemotron Research Reasoning Qwen 1.5B v2 RLVE

This model is trained on top of Nemotron-Research-Reasoning-Qwen-1.5B using RLVE. For more details on RLVE, check out the figure below, or see our paper for more details.

Evaluation Results

We provide evaluation instructions in our repository.

Benchmark	AIME 2024 (Avg@64)	AIME 2025 (Avg@64)	OMEGA-500 (Avg@4)	OlympiadBench (Avg@4)	BBEH (Avg@4)	LiveCodeBench-v6 (Pass@8)
Nemotron-Research-Reasoning-Qwen-1.5B-v2 (starting model)	51.93	33.96	24.15	57.85	7.27	25.90
Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE	56.51	39.84	27.75	60.56	9.10	27.49

Intended uses & limitations

CC-BY-NC-4.0, inherited from starting model (Nemotron-Research-Reasoning-Qwen-1.5B-v2).

Training

For training details and hyperparameters. please see our repository.

In particular, you can rerun training for this model with this command (after setting up the repository):

bash scripts/training/Nemotron-Research-Reasoning-Qwen-1.5B-v2/rlve/num-environment=400.sh RLVE

Citation

@article{zeng2025rlve,
  title={RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments},
  author={Zeng, Zhiyuan and Ivison, Hamish and Wang, Yiping and Yuan, Lifan and Li, Shuyue Stella and Ye, Zhuorui and Li, Siting and He, Jacqueline and Zhou, Runlong and Chen, Tong and Zhao, Chenyang and Tsvetkov, Yulia and Du, Simon Shaolei and Jaques, Natasha and Peng, Hao and Koh, Pang Wei and Hajishirzi, Hannaneh},
  journal={arXiv preprint 2511.07317},
  year={2025}
}