nanoGPT speedrun
Train GPT-2 small to a fixed validation loss in as little time as possible (placeholder)
Start unet-value-embeds
浏览文件+16 −0 routes/unet-value-embeds/README.md 新增 查看文件
| @@ -0,0 +1,16 @@ | ||
| 1 | +--- | |
| 2 | +issue: 3 | |
| 3 | +status: working | |
| 4 | +tags: model | |
| 5 | +--- | |
| 6 | +# unet-value-embeds | |
| 7 | + | |
| 8 | +U-net skip connections and value embeddings. | |
| 9 | + | |
| 10 | +## What happened | |
| 11 | + | |
| 12 | +- Started. | |
| 13 | + | |
| 14 | +## Next | |
| 15 | + | |
| 16 | +Sliding-window attention to cut the compute. | |