Instructions to use rLLM/rLLM-FinQA-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rLLM/rLLM-FinQA-4B with Transformers:

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

pipe = pipeline("text-generation", model="rLLM/rLLM-FinQA-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rLLM/rLLM-FinQA-4B")
model = AutoModelForCausalLM.from_pretrained("rLLM/rLLM-FinQA-4B")
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 rLLM/rLLM-FinQA-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rLLM/rLLM-FinQA-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rLLM/rLLM-FinQA-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rLLM/rLLM-FinQA-4B

SGLang

How to use rLLM/rLLM-FinQA-4B 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 "rLLM/rLLM-FinQA-4B" \
    --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": "rLLM/rLLM-FinQA-4B",
		"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 "rLLM/rLLM-FinQA-4B" \
        --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": "rLLM/rLLM-FinQA-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rLLM/rLLM-FinQA-4B with Docker Model Runner:
```
docker model run hf.co/rLLM/rLLM-FinQA-4B
```

FinQA

Training Financial Agents with Reinforcement Learning

FinQA Overview

FinQA is a financial question-answering agent fine-tuned from Qwen3-4B-Instruct-2507 using reinforcement learning (RL). The model answers questions about SEC 10-K financial statements using specialized tools (SQL queries, table lookup, calculators), achieving 59.70% accuracy on Snorkel Finance Benchmark and 26.6% on Snorkel Finance Reasoning.

Data

Our training dataset is built from SEC 10-K filings and consists of 5,110 question-answer pairs across:

207 companies spanning multiple sectors
6,923 financial tables extracted from 10-K filings
Single-table questions: Direct lookups and calculations from individual tables
Multi-table questions: Cross-table reasoning requiring data from multiple sources

The dataset is available on HuggingFace.

Tools

The agent uses 4 specialized tools for financial analysis:

Tool	Description
`get_table_names`	List available tables for a given company
`get_table_info`	Get table metadata, columns, dtypes, and sample values
`sql_query`	Execute SQL queries on financial tables (SQLite)
`calculator`	Evaluate mathematical expressions

Training

We fine-tune Qwen3-4B-Instruct-2507 using GRPO with LLM-as-judge rewards for correctness evaluation. A more detailed description of the training recipe can be found in our documentation.

Evaluation

Model	FinQA	FinQA Reasoning
Qwen3-4B-Instruct-2507 (Base)	27.90%	13.90%
gpt-5-nano-2025-08-07	50.00%	26.60%
Qwen3-235B-A22B	51.37%	18.90%
rLLM-FinQA-4B (Ours)	59.70%	26.60%
Gemini-2.5-Pro-Preview	60.60%	34.60%
GPT-4.1-2025-04-14	62.70%	37.90%
o3-mini-2025-01-31	63.79%	30.37%

Serving FinQA

Start a vLLM server and run the agent:

python -m vllm.entrypoints.openai.api_server \
    --model rLLM/rLLM-FinQA-4B \
    --host 0.0.0.0 \
    --port 30000 \
    --dtype bfloat16

python -m projects.finqa.run_finqa

For detailed setup instructions, see the project README.

Acknowledgement

This is a joint collaboration between the rLLM team at UC Berkeley and Snorkel AI.
Our model is trained on top of Qwen3-4B-Instruct-2507.
Our work is done as part of Berkeley Sky Computing Lab.

Citation

@misc{rllm2026finqa,
  title={FinQA: Training Financial Agents with Reinforcement Learning},
  author={Manan Roongta and Sijun Tan and Bhavishya Pohani and Charles Dickens and Christopher Glaze},
  year={2026},
  howpublished={\url{https://rllm-project.com/post.html?post=finqa.md}},
  note={Blog Post}
}

Downloads last month: 60

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for rLLM/rLLM-FinQA-4B

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1714)

this model

rLLM
/

rLLM-FinQA-4B