Tag
A local web UI for finetuning AI models on personal text, featuring live gradient activity monitoring, A/B prompt comparison, and AMD ROCm compatibility.
A tweet claiming that Chinese open-source LLMs have completely replaced newly released models, allowing local training, though raising the bar for casual developers.
The author details attempts to locally train a Qwen 3.6 27B autoregressive-to-diffusion model on an Nvidia 5090 GPU using qlora and modifications from open-dllm and d3LLM, facing VRAM constraints and hardware issues while exploring one-shot diffusion techniques.