59 lines
2.0 KiB
Markdown
59 lines
2.0 KiB
Markdown
---
|
|
license: llama3.1
|
|
datasets:
|
|
- TheFinAI/Fino1_Reasoning_Path_FinQA
|
|
language:
|
|
- en
|
|
base_model:
|
|
- meta-llama/Llama-3.1-8B-Instruct
|
|
pipeline_tag: text-generation
|
|
---
|
|
# 🦙 Fino1-8B
|
|
|
|
**Fino1-8B** is a fine-tuned version of **Llama 3.1 8B Instruct**, designed to improve performance on **[financial reasoning tasks]**. This model has been trained using **SFT** and **RF** on **TheFinAI/Fino1_Reasoning_Path_FinQA**, enhancing its capabilities in **financial reasoning tasks**.
|
|
Check our paper arxiv.org/abs/2502.08127 for more details.
|
|
|
|
## 📌 Model 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
|
|
- **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]`
|
|
|
|
## 🔧 Usage
|
|
To use `Fino1-8B` with Hugging Face's `transformers` library:
|
|
|
|
```python
|
|
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))
|
|
```
|
|
|
|
## 💡 Citation
|
|
|
|
If you use this model in your research, please cite:
|
|
```python
|
|
@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}
|
|
} |