Instructions to use kiyam/ddro-msmarco-pq-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kiyam/ddro-msmarco-pq-sft with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kiyam/ddro-msmarco-pq-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("kiyam/ddro-msmarco-pq-sft")
model = AutoModelForSeq2SeqLM.from_pretrained("kiyam/ddro-msmarco-pq-sft")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kiyam/ddro-msmarco-pq-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kiyam/ddro-msmarco-pq-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kiyam/ddro-msmarco-pq-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kiyam/ddro-msmarco-pq-sft

SGLang

How to use kiyam/ddro-msmarco-pq-sft with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kiyam/ddro-msmarco-pq-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kiyam/ddro-msmarco-pq-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kiyam/ddro-msmarco-pq-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kiyam/ddro-msmarco-pq-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kiyam/ddro-msmarco-pq-sft with Docker Model Runner:
```
docker model run hf.co/kiyam/ddro-msmarco-pq-sft
```

DDRO Step-2 SFT Reference Policy — MS MARCO + PQ

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-msmarco-pq

How to load

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

repo = "kiyam/ddro-msmarco-pq-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.

Downloads last month: 12

Safetensors

Model size

0.3B params

Tensor type

F32

Collection including kiyam/ddro-msmarco-pq-sft

DDRO-Reference-Policies (SFT)

Collection

Step-2 SFT reference policies (π_ref) used to initialize DDRO (MS MARCO / NQ; PQ and Title+URL DocIDs); use these for fair comparisons/ablations. • 4 items • Updated Dec 16, 2025