My LLM fine-tuning, RAG evaluation, and agent projects, collected in one repo. Each project lives in its own folder with its own README, requirements, and results. The original repos' commit history is preserved.
| Project | What it does | Headline result |
|---|---|---|
finetuning/smolvlm-pokemon-cards |
Fine-tunes SmolVLM2-500M to read Pokémon TCG cards and return structured JSON (name, HP, set). Trained on Modal, 1x H100. | 86% exact match vs. 0% for the base model |
finetuning/qwen-gemma-text-to-sql |
QLoRA (Unsloth) fine-tuning of Qwen3-4B and Gemma 3 4B-IT on Spider 1.0 text-to-SQL, scored by running the SQL against the real Spider databases. | Qwen3-4B: 3.3% → 80.0% execution accuracy |
| Project | What it does | Headline result |
|---|---|---|
rag/rag-paradigm-comparison |
Compares Vector, Hybrid (BM25 + dense, RRF), Vectorless, and Graph RAG on a synthetic enterprise corpus (finance, marketing, product, service), with LLM-judge scores and retrieval hit rate. | Hybrid wins on structured/financial docs (4.90/5); Vector wins on paraphrased and unstructured queries |
| Project | What it does | Stack |
|---|---|---|
agents/nemotron-computer-use |
A voice + vision agent that controls macOS. Each step sends a screenshot to the model, gets back exactly one JSON action (click / type / key / scroll / open_app / done), with coordinates normalized to a 0–1000 grid, runs it, and repeats. | NVIDIA Nemotron 3.5 Super VL (120B-A12B MoE) served with vLLM on Modal, 4x H100 TP=4, MTP speculative decoding, OpenAI-compatible API. Local Whisper-large-v3-turbo (MLX) for speech-to-text |
finetuning/
smolvlm-pokemon-cards/ # VLM fine-tune: train.py, modal_train.py, notebook, plots
qwen-gemma-text-to-sql/ # QLoRA text-to-SQL notebook + benchmark
agents/
nemotron-computer-use/ # serve.py (Modal + vLLM), agent.py loop, computer.py, voice.py
rag/
rag-paradigm-comparison/ # src/, eval sets, results/, paper
Each project is self-contained. cd into its folder and follow that README's setup steps.
These projects started as separate repos, which are now consolidated here:
finetuned-vllm, qwen-gemma4b-finetuned, rag-comparison.