Instructions to use TheFinAI/Fin-o1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheFinAI/Fin-o1-8B with Transformers:

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

pipe = pipeline("text-generation", model="TheFinAI/Fin-o1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheFinAI/Fin-o1-8B")
model = AutoModelForCausalLM.from_pretrained("TheFinAI/Fin-o1-8B", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheFinAI/Fin-o1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheFinAI/Fin-o1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheFinAI/Fin-o1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheFinAI/Fin-o1-8B

SGLang

How to use TheFinAI/Fin-o1-8B 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 "TheFinAI/Fin-o1-8B" \
    --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": "TheFinAI/Fin-o1-8B",
		"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 "TheFinAI/Fin-o1-8B" \
        --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": "TheFinAI/Fin-o1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheFinAI/Fin-o1-8B with Docker Model Runner:
```
docker model run hf.co/TheFinAI/Fin-o1-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Request access to Fin-o1-8B

Fin-o1-8B is released by The Fin AI for research. Access is granted automatically after you complete this short form.

This model is released for research purposes. It must not be used to provide personalized investment advice or to make automated financial decisions without human oversight. Use is also subject to the license of the base model (Qwen3, Apache 2.0).

Fin-o1-8B

📄 Paper · 🤗 Collection · 💻 Code · 🏆 Leaderboard · 🌐 The Fin AI

Fin-o1-8B is a financial reasoning model fine-tuned from Qwen3-8B with supervised fine-tuning on financial chain-of-thought data followed by GRPO reinforcement learning. It was introduced in Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance (arXiv:2502.08127).

Fin-o1 vs. Fino1. The two families come from the same paper but are different generations:

Fino1 (2025-02/03) Fin-o1 (2025-05)

8B Fino1-8B — Llama-3.1-8B-Instruct Fin-o1-8B — Qwen3-8B

14B Fino1-14B — Qwen2.5-14B-Instruct Fin-o1-14B — Qwen3-14B

Training CoT SFT + RL SFT + GRPO

For new work we recommend the Fin-o1 models.

	Fino1 (2025-02/03)	Fin-o1 (2025-05)
8B	Fino1-8B — Llama-3.1-8B-Instruct	Fin-o1-8B — Qwen3-8B
14B	Fino1-14B — Qwen2.5-14B-Instruct	Fin-o1-14B — Qwen3-14B
Training	CoT SFT + RL	SFT + GRPO

Model Details


Base model	Qwen/Qwen3-8B
Architecture	Qwen3ForCausalLM, 36 layers, hidden size 4096
Precision	bfloat16
Context length	40,960 tokens (`max_position_embeddings`)
Training data	TheFinAI/FinCoT — reasoning paths derived from FinQA, TAT-QA, DocMath-Eval, Econ-Logic, BizBench-QA and DocFinQA
Training method	SFT, then GRPO with accuracy and format rewards
Language	English
License	Apache 2.0 (same as the base model)

GRPO stage (from `trainer_state.json` / `train_results.json` in this repo)


Steps / epochs	500 steps, 2 epochs
Training samples	1,525
Per-device batch size	2
Peak learning rate	3e-6
Rewards	`accuracy_reward`, `format_reward`
Wall-clock	≈ 2.2 h

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "TheFinAI/Fin-o1-8B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")

messages = [{
    "role": "user",
    "content": "A company's revenue grew from $120M to $150M while operating costs rose from $90M to $105M. "
               "By how many percentage points did the operating margin change?",
}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)
output = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Evaluation

Fin-o1 and Fino1 are evaluated on FinQA, DocMath-Eval (simple / complex long), XBRL-Math and related financial reasoning tasks. See the paper and the Open FinLLM Reasoning Leaderboard for results.

Intended Use & Limitations

Intended use: research on financial numerical reasoning, question answering over financial text and tables, and as a baseline for financial reasoning models.
Not intended for: investment advice, trading decisions, or any automated financial decision without human review.
The model can produce incorrect calculations or hallucinated figures, especially on long documents with multiple tables.
Trained and evaluated on English data only.

Citation

@misc{qian2025fino1transferabilityreasoningenhancedllms,
      title={Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance},
      author={Lingfei Qian and Weipeng Zhou and Yan Wang and Xueqing Peng and Han Yi and Yilun Zhao and Jimin Huang and Qianqian Xie and Jian-yun Nie},
      year={2025},
      eprint={2502.08127},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.08127},
}