Update README.md

README.md

@@ -3,56 +3,31 @@ base_model: microsoft/Phi-3-mini-4k-instruct
 library_name: transformers
 model_name: adapter
 tags:
-- generated_from_trainer
+- financial-qa
+- phi3-mini
 - sft
 - trl
-licence: license
+- annual-reports
+license: apache-2.0
 ---
 
-# Model Card for adapter
+# Model Card: phi3-mini-finance-nlp
 
-This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/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.
 
-## Quick start
+## 🔍 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
 
 ```python
 from transformers import pipeline
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
+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"])
-```
-
-## Training procedure
-
- 
-
-
-This model was trained with SFT.
-
-### Framework versions
-
-- TRL: 0.19.1
-- Transformers: 4.53.1
-- Pytorch: 2.6.0+cu124
-- Datasets: 4.0.0
-- Tokenizers: 0.21.2
-
-## Citations
-
-
-
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```