Downloads · 30 days
0
financial-risk-extractor-phi3-qlora
Dino21/financial-risk-extractor-phi3-qlora
financial-risk-extractor-phi3-qlora is a text generation model from Dino21. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as mit.
Extracts structured risk factors from corporate disclosure prose.
Access
Public
Updated Oct 15, 2026
Parameters
3.8B
7.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- mit
- Model type
- phi3
- Access
- Public
- Created
- Sep 1, 2026
- Updated
- Oct 15, 2026
- SHA
- 7c42d16b
Try a prompt
Base models
Model card
From the Hugging Face model README
Financial Risk Clause Extractor (Phi-3-mini, QLoRA)
Extracts structured risk factors from corporate disclosure prose.
Input: a passage of filing-style text. Output: JSON listing each distinct risk with a category from a closed twelve-item taxonomy, its trigger, its potential impact, and a severity.
Taxonomy
market_risk, credit_risk, liquidity_risk, operational_risk,
regulatory_risk, cybersecurity_risk, supply_chain_risk,
concentration_risk, geopolitical_risk, technology_risk,
litigation_risk, environmental_risk
Training
| Base | microsoft/Phi-3-mini-4k-instruct |
| Method | QLoRA, 4-bit NF4 with double quantisation |
| LoRA | r=16, alpha=32, dropout 0.05 |
| Target modules | qkv_proj, o_proj, gate_up_proj, down_proj |
| Data | 120 synthetic examples, 96 train / 12 val / 12 test |
| Epochs | 2, selected on validation loss |
| Hardware | single Colab T4, 6.2 minutes of training |
Validation loss decreased from 0.6284 to 0.6098 across two epochs. A 3-epoch run was tried first and showed validation loss rising at epoch 3 while training loss kept falling, so 2 was chosen on that evidence.
Training data was generated synthetically by a teacher model. Passages are invented, not real filings, and no real company is named.
Intended use
A portfolio project demonstrating QLoRA fine-tuning for structured extraction. Not investment advice, and not validated for production use on real regulatory filings.
Repository
Full pipeline, dataset generation, diversity analysis and evaluation: https://github.com/Dinojan9901/llm-financial-research-agents
- Task
- Text Generation
- Library
- peft
- Type
- phi3
- License
- mit
- Languages
- en
- Created
- Sep 1, 2026
- Updated
- Oct 15, 2026