LoRA adapter for Smoltaur-0.1B, fine-tuned on the full Psych-101 as part of the LoRA-rank sweep and dataset-size ablation for Small Foundation Models of Human Cognition and Behaviour.
| field | value |
|---|---|
| base model | unsloth/SmolLM2-135M |
| LoRA rank | 16 (alpha = rank, rsLoRA) |
| data fraction | 100% of Psych-101 |
| training | 1 epoch, completion-only loss, seed 3407 |
Load with PEFT on top of unsloth/SmolLM2-135M, or evaluate with the project's
eval_model.py --backend unsloth.
adapter_model.safetensors 20 MBcheckpoint-1000/adapter_model.safetensors 20 MBcheckpoint-1500/adapter_model.safetensors 20 MBcheckpoint-1878/adapter_model.safetensors 20 MBcheckpoint-500/adapter_model.safetensors 20 MBcheckpoint-1000/optimizer.pt 11 MBcheckpoint-1500/optimizer.pt 11 MBcheckpoint-1878/optimizer.pt 11 MBcheckpoint-500/optimizer.pt 11 MBcheckpoint-1000/rng_state.pth 14.6 kBcheckpoint-1500/rng_state.pth 14.6 kBcheckpoint-1878/rng_state.pth 14.6 kBcheckpoint-500/rng_state.pth 14.6 kBcheckpoint-1000/training_args.bin 5.8 kBcheckpoint-1500/training_args.bin 5.8 kBcheckpoint-1878/training_args.bin 5.8 kBcheckpoint-500/training_args.bin 5.8 kBtraining_args.bin 5.8 kBcheckpoint-1000/scheduler.pt 1.5 kBcheckpoint-1500/scheduler.pt 1.5 kBcheckpoint-1878/scheduler.pt 1.5 kBcheckpoint-500/scheduler.pt 1.5 kBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo socius/Smoltaur-0.1B-LoRA-r16 ./model-folderunsloth/SmolLM2-135M