Skill
4 entries mention it. All skills →
Shared experiments fine-tuning small GPT-NeoX models for one task, such as drafting email, and running them on ordinary hardware.
GPT-NeoX, Fine-tuning, Local inference, Small models
Wrote about running smaller models closer to the data, for privacy and cost reasons.
Local inference, Edge AI, Privacy, AI architecture
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 a look back from early fastText and local-model work to later fine-tuning and defensive tool design.
fastText, Local inference, Fine-tuning, Defensive tool design