Skill
3 entries mention it. All skills →
Fine-tuned Llama and OpenChat-class models locally with llama.cpp: preparing the training data, training, and checking the results.
llama.cpp, SFT, LoRA, Dataset engineering, Local inference
Wrote publicly about using reinforcement learning and supervised fine-tuning to study reasoning in small models.
Reinforcement learning, SFT, Small models, Reasoning-model training
Developed training tooling for Apple Silicon, with configurable tasks, evaluators, rewards, supervised modes and guided reasoning experiments.
MLX, Python, GRPO, LoRA, SFT, Reward design, Training infrastructure