Fino1 - 8B Open-source Financial Inference AI Model - Optimized based on Llama 3.1, Free to Enhance Financial Inference Performance

Fino1 8B

Developed by TheFinAI

Fino1-8B is a fine-tuned version based on Llama 3.1 8B Instruct, focusing on improving performance in financial reasoning tasks.

Large Language Model

Safetensors

English#Financial Reasoning Enhancement #Mathematical Calculation Optimization #SFT Fine-tuning

Downloads 697

Release Time : 2/12/2025

Model Overview

This model was trained on TheFinAI/Fino1_Reasoning_Path_FinQA dataset using SFT and RF, enhancing its capabilities in financial mathematical reasoning tasks.

Model Features

Financial Reasoning Enhancement

Fine-tuned with specific financial datasets to significantly improve financial mathematical reasoning capabilities.

Based on Llama 3.1

Inherits the robust foundational capabilities of Llama 3.1 8B Instruct.

SFT and RF Training

Utilizes Supervised Fine-Tuning (SFT) and Reward Modeling (RF) methods to optimize performance.

Model Capabilities

Financial Mathematical Reasoning

Text Generation

Numerical Calculation

Use Cases

Financial Analysis

Financial Statement Analysis

Parse and reason about financial statement data

Improves accuracy in understanding financial data

Financial Math Problem Solving

Solve complex financial math problems

Provides accurate numerical calculation results

🚀 🦙 Fino1-8B

Fino1-8B is a fine - tuned version of Llama 3.1 8B Instruct. It aims to enhance performance on [financial reasoning tasks]. The model has been trained using SFT and RF on TheFinAI/Fino1_Reasoning_Path_FinQA, which improves its capabilities in financial reasoning tasks. Check our paper arxiv.org/abs/2502.08127 for more details.

📚 Documentation

✨ Features

Fine - Tuned: Based on Meta Llama 3.1 8B Instruct, fine - tuned to boost performance on financial reasoning tasks.
Training Data: Utilizes TheFinAI/Fino1_Reasoning_Path_FinQA dataset derived from FinQA.
Training Method: Employs SFT and RF for training.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

To use Fino1-8B with Hugging Face's transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "TheFinAI/Fino1-8B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

input_text = "What is the results of 3-5?"
inputs = tokenizer(input_text, return_tensors="pt")

output = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(output[0], skip_special_tokens=True))

📋 Model Details

Property	Details
Model Name	`Fino1-8B`
Base Model	`Meta Llama 3.1 8B Instruct`
Fine - Tuned On	`TheFinAI/Fino1_Reasoning_Path_FinQA` (Derived from FinQA dataset)
Training Method	SFT and RF
Objective	`[Enhance performance on specific tasks such as financial mathemtical reasoning]`
Tokenizer	Inherited from `Llama 3.1 8B Instruct`

📊 Training Configuration

Property	Details
Training Hardware	`GPU: [e.g., 4xH100]`
Batch Size	`[e.g., 16]`
Learning Rate	`[e.g., 2e-5]`
Epochs	`[e.g., 3]`
Optimizer	`[e.g., AdamW, LAMB]`

📄 License

The model is under the llama3.1 license.

💡 Citation

If you use this model in your research, please cite:

@article{qian2025fino1,
  title={Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance},
  author={Qian, Lingfei and Zhou, Weipeng and Wang, Yan and Peng, Xueqing and Huang, Jimin and Xie, Qianqian},
  journal={arXiv preprint arXiv:2502.08127},
  year={2025}
}

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご