Unclaimed profileBuilt from public GitHub and Hugging Face activity. Daoyuan has not joined Lounge yet.Claim it
Not on Lounge yet
Daoyuan Li
developerBuilds can-i-finetune-this · Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and l
Public projects
can-i-finetune-this
Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.
Pythonbitsandbytesfine-tuninggpu
mini-verl
verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.
Pythonagentic-rlalignmentconsumer-gpu
pairjudge
Pairwise LLM judges (A/B/tie): budget-aware multi-turn packing, position-bias correction, pseudo-label distillation. Generalized from the 4th-place (gold) solution to Kaggle LMSYS Chatbot Arena.
Pythonchatbot-arenagold-medalkaggle-competition
tracedistill
Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).
Pythonchain-of-thoughtfine-tuningkaggle
RepoGuardBench
Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.
Pythonai-securitybenchmarkcoding-agents
llama3-emotion-lora
Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.
Pythonemotion-classificationfine-tuningflash-attention
Likely stack
LlamaPyTorchTransformersMCPFastAPI
