Current Focus:
- Building AI-driven financial analysis tools leveraging LLMs and reinforcement learning
- Training small-scale language models for specialized reasoning tasks
- Exploring Group Relative Policy Optimization (GRPO) for model alignment
- Developing mathematical visualization tools with Manim
Expertise Areas:
- CFA training, Derivatives, and Options Trading
- Congressional Trading Analysis and Market Microstructure
- Quantitative Finance and Risk Management
- Machine Learning Engineering (PyTorch, TensorFlow)
- Mathematical Visualization and 3D Graphics
Learning Journey:
- Advanced PyTorch implementations
- Reinforcement Learning from Human Feedback (RLHF)
- Large Language Model fine-tuning and alignment
- Computational geometry and fractal mathematics
I once got Karpathy to reply "Nice."
My meager Google Scholar reference
| Category | Date | Headline |
|---|---|---|
| Market | Oct 24, 2025 | China strikes conciliatory tone ahead of expected Trump-Xi meeting |
| Market | Oct 23, 2025 | With stock market concentration risk at peak, 'it's cash, precious metals, and then crypto' as ne... |
| Market | Oct 24, 2025 | China vows to boost domestic consumption, tech self-reliance in next five years as Fourth Plenum ... |
| Market | Oct 23, 2025 | China's property slump is far from bottoming. But Beijing is prioritizing tech growth |
| Market | Oct 22, 2025 | Western Alliance CEO says alleged loan fraud is 'incredibly frustrating' but isolated issue |
| Finance | Oct 24, 2025 | Trump clears way for new China tariffs and hits out at Canada |
| Finance | Oct 24, 2025 | Canada’s PM Carney courts Asia to cut economic dependence on US |
| Finance | Oct 25, 2025 | How fan power is reshaping pop |
| Finance | Oct 25, 2025 | Starmer needs to get serious about governing — and quick |
| Finance | Oct 25, 2025 | The Temu theory of populism |
|
3D visualization of options volatility skew across strikes and maturities. This surface represents the Black-Scholes implied volatility smile, crucial for pricing exotic derivatives and understanding market risk premia. |
A fractal Archimedean solid demonstrating computational complexity in 3D geometry. Each vertex recursively contains another complete polyhedron, requiring precise transformations across 62 unique faces - a challenging test case for LLM mathematical reasoning. |
- Volatility Surface: Real-time Black-Scholes implied volatility calculations
- 3D Rendering: Custom Manim animations for financial mathematics
- Computational Geometry: Precise coordinate transformations in 3D space
- Data Visualization: Market data analysis and pattern recognition
As of Oct 2025: 6 models / 4 datasets / 6 Spaces. Below are the ones reviewers should try first:
| Model (HF) | Focus | Base |
|---|---|---|
| Qwen.5B-OpenR1Math | Reasoning on math steps & answers (Open-R1 style) | Qwen/Qwen2.5-0.5B-Instruct |
| Qwen.5B-GSM8K | Small-model math finetune (GSM8K emphasis) | Qwen/Qwen2.5-0.5B-Instruct |
| GRPOtuned / GRPOtuned2 | GRPO experiments on 0.5B LLMs | Qwen/Qwen2.5-0.5B-Instruct |
Direct links:
- Models: Qwen.5B-OpenR1Math, Qwen.5B-GSM8K, GRPOtuned, GRPOtuned2
- Datasets: synthetic_stoney_data, StoneyNakoda
- Spaces (demos): deepsitecoder, Stoney-1, Ask About Stoney
Quickstart (try a model in 5 lines):
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
mdl = "HarleyCooper/Qwen.5B-OpenR1Math" # switch to any of your model IDs
tok = AutoTokenizer.from_pretrained(mdl)
model = AutoModelForCausalLM.from_pretrained(mdl, torch_dtype=torch.float16, device_map="auto")
print(tok.decode(model.generate(**tok("Solve: 13*17", return_tensors="pt").to(model.device), max_new_tokens=64)[0], skip_special_tokens=True))