Hugging Face's logo

socius
/
Llama-Centaur-8B-LoRA-r4

Text Generation
PEFT
Safetensors
English
psychology
cognitive science
human behavior
unsloth
lora
Model card Files
xet
 Community
Llama-Centaur-8B-LoRA-r4

Meta Llama

socius Paper Parameters LoRA Dataset

Llama-Centaur-8B-LoRA-r4

LoRA adapter for Llama-Centaur-8B, 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-3.1-8B
LoRA rank 4 (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-3.1-8B, or evaluate with the project's eval_model.py --backend unsloth.

Downloads last month
10
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for socius/Llama-Centaur-8B-LoRA-r4

Base model

meta-llama/Llama-3.1-8B
Finetuned
unsloth/Llama-3.1-8B
Adapter
(16)
this model

Dataset used to train socius/Llama-Centaur-8B-LoRA-r4

Collection including socius/Llama-Centaur-8B-LoRA-r4

Paper for socius/Llama-Centaur-8B-LoRA-r4