Downloads · 30 days
0
thesis-loras-sdf-ablation
BeschB/thesis-loras-sdf-ablation
thesis-loras-sdf-ablation is a machine learning model from BeschB. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
LoRA adapters (rank 64, alpha 128) from the Synthetic Document Finetuning (SDF) stage, comparing 10k vs 50k training documents per persona (Thesis Chapter 4, Experiment 1 / H1, Tables eval-overall-llama / eval-overall…
Access
Public
Updated Aug 9, 2026
Repo size
4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 GB · 96%
At a glance
- Access
- Public
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026
- SHA
- 70e531ec
Model card
From the Hugging Face model README
Experiment 1: SDF trained on 10k vs 50k synthetic documents
LoRA adapters (rank 64, alpha 128) from the Synthetic Document Finetuning (SDF) stage, comparing 10k vs 50k training documents per persona (Thesis Chapter 4, Experiment 1 / H1, Tables eval-overall-llama / eval-overall-olmo).
Layout: {llama,olmo}-sdf-{10k,50k}/{goodness,misaligned,sarcasm}/
Base models (merge/load the LoRA on top of these):
llama-*/Olmo-*(capital O) adapters: meta-llama/Llama-3.1-8B-Instructolmo-*(lowercase o) adapters: allenai/Olmo-3-7B-Instruct-SFT
Loss is computed pretrain-style (all tokens) over third-person synthetic
documents -- see BeschB/thesis-training-data (sdf_docs/{10k,50k}) for
the underlying training documents.
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026