metadata
license: mit
datasets:
- FinGPT/fingpt-sentiment-train
language:
- en
base_model:
- HuggingFaceTB/SmolLM2-1.7B-Instruct
pipeline_tag: text-classification
library_name: peft
tags:
- text-generation-inference
- finance
Model Card for FlowerTune-SmolLM2-1.7B-Instruct-Finance-PEFT
Evaluation Results (Accuracy)
- FiQA: 56.58 %
- FPB: 71.37 %
- TFNS: 75.75 %
- Average: 67.90 %
Model Details
This PEFT adapter has been trained by using Flower, a friendly federated AI framework.
The adapter and benchmark results have been submitted to the FlowerTune LLM Finance Leaderboard.
Please check the following GitHub project for details on how to reproduce training and evaluation steps:
https://github.com/ethicalabs-ai/FlowerTune-SmolLM2-1.7B-Instruct-Finance/