ML Engineer | Game Dev | Full Stack Developer
Model Training & Finetuning
- LoRA / QLoRA finetuning
- Full parameter training
- Dataset preprocessing & curation
- Training on Kaggle / cloud GPUs
Model Merging
- Model merging techniques
- Weight interpolation
- Multi-model ensembles
|
LLM inference in C/C++ with CUDA support |
Async Stable Diffusion integration for SillyTavern |
|
TTS pipeline for ComfyUI using Qwen models |
Navigation lock extension for SillyTavern |

