Llama-Centaur-3B-LoRA
Collection
5 items • Updated • 3
Llama-Centaur-3B-LoRA-r16
LoRA adapter for Llama-Centaur-3B, 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/Llama-3.2-3B |
| 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/Llama-3.2-3B, or evaluate with the project's
eval_model.py --backend unsloth.
- Downloads last month
- 17