Downloads · 30 days
15
14% of all-time downloads
ddro-nq-tu-sft
kiyam/ddro-nq-tu-sft
ddro-nq-tu-sft is a text generation model from kiyam. Use it when you need the model to write or continue text. It is set up for transformers.
This repository contains the Step 2 (SFT) checkpoint used as the reference policy (πref) / initialization for the DDRO training stage from Lightweight and Direct Document Relevance Optimization for Generative Informat…
All-time downloads
107
Public
Parameters
228M
911 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors911 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- t5
- Access
- Public
- Created
- Dec 16, 2025
- Updated
- Dec 16, 2025
- SHA
- 87e3beb2
Try a prompt
Model card
From the Hugging Face model README
DDRO Step-2 SFT Reference Policy — NQ + TU (Title/URL)
This repository contains the Step 2 (SFT) checkpoint used as the reference policy (π_ref) / initialization for the DDRO training stage from Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval.
What this is
- Stage: Step 2 / supervised fine-tuning (SFT)
- Role in DDRO: reference policy (π_ref)
Corresponding final DDRO model
- Post-DDRO (Step 3) checkpoint:
kiyam/ddro-nq-tu
How to load
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
repo = "kiyam/ddro-nq-tu-sft"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSeq2SeqLM.from_pretrained(repo)
Intended use
Research and reproducibility. Please cite the DDRO paper if you use this checkpoint.
- Task
- Text Generation
- Library
- transformers
- Type
- t5
- Languages
- en
- Created
- Dec 16, 2025
- Updated
- Dec 16, 2025