Question Answering
Transformers
Safetensors
English
Chinese
qwen3
text-generation
finance
reasoning
chain-of-thought
financial-analysis
text-generation-inference
Instructions to use OpenDataArena/ODA-Fin-SFT-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenDataArena/ODA-Fin-SFT-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="OpenDataArena/ODA-Fin-SFT-8B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("OpenDataArena/ODA-Fin-SFT-8B") model = AutoModelForCausalLM.from_pretrained("OpenDataArena/ODA-Fin-SFT-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
library_name: transformers
license: apache-2.0
base_model:
- Qwen/Qwen3-8B
tags:
- finance
model-index:
- name: ODA-Fin-SFT-8B
results: []
datasets:
- OpenDataArena/ODA-Fin-SFT-318k
language:
- en
- zh
metrics:
- accuracy
- f1
pipeline_tag: question-answering
Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training
馃摉 Model Summary
ODA-Fin-SFT-8B is an 8B financial large language model fine-tuned on ODA-Fin-SFT-318k, a high-quality distilled financial dataset with strong Chain-of-Thought reasoning capabilities.
It is built on Qwen3-8B and optimized for financial understanding, sentiment analysis, and numerical reasoning over text and tables.
馃搱 Performance
ODA-Fin-SFT-8B achieves strong performance across 9 financial benchmarks.

