Downloads · 30 days
9
4% of all-time downloads
sentence-selection-orpo-lora
debaterhub/sentence-selection-orpo-lora
sentence-selection-orpo-lora is a machine learning model from debaterhub. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
Fine-tuned LoRA adapter for sentence selection in debate contexts.
All-time downloads
204
Public
Repo size
53.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors53.5 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jan 6, 2026
- Updated
- Jan 6, 2026
- SHA
- bb62db0c
Base models
Model card
From the Hugging Face model README
Sentence Selection ORPO LoRA
Fine-tuned LoRA adapter for sentence selection in debate contexts.
Training Details
- Base Model: Qwen3-30B-A3B (via SFT fine-tuned version)
- Method: ORPO (Odds Ratio Preference Optimization)
- Task: Select relevant sentence IDs from academic texts to support claims
- F1 Score: 0.247 on holdout set
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-30B-A3B")
model = PeftModel.from_pretrained(base_model, "debaterhub/sentence-selection-orpo-lora")
Key Findings
- Format-consistent DPO pairs essential for ORPO training
- 2 epochs optimal (more causes overfitting)
- Noise augmentation fixes positional bias in training data
- Library
- peft
- Created
- Jan 6, 2026
- Updated
- Jan 6, 2026