MakazhanAlpamys
Every MakazhanAlpamys project, model and release Early Signal has spotted, newest first.
| Signal | Peak day | Total |
|---|---|---|
| Repo · MakazhanAlpamys/SoupFine-tune an 8B LLM on a 4 GB Laptop GPUSoup lets you fine-tune large language models with a single YAML file and a one-line command, handling all the plumbing for you. Its layer-streaming technique keeps the frozen base out of VRAM, so an 8-billion-parameter model can be trained on a laptop GPU with just 4 GB of memory. | ▲ 227 | 10k |