metadata
base_model: microsoft/Phi-3-mini-4k-instruct
library_name: transformers
model_name: adapter
tags:
- financial-qa
- phi3-mini
- sft
- trl
- annual-reports
license: apache-2.0
Model Card: phi3-mini-finance-nlp
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on financial document Q&A — trained on custom datasets consisting of Indian company annual reports and disclosures. It is tailored to handle long-form financial questions such as corporate strategy, CSR responsibilities, market capitalization insights, and board governance.
🔍 Use Case
This model can:
- Extract insights from annual reports.
- Answer questions on topics like CSR, supply chain, revenue breakdown, and director messages.
- Assist in financial document summarization and intelligent retrieval for policy/analysis.
🚀 Quick Start
from transformers import pipeline
question = "What is the company's approach to CSR in the 2023 annual report?"
generator = pipeline("text-generation", model="sweatSmile/phi3-mini-finance-nlp", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])