Instructions to use PaSaMaster/Ranker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PaSaMaster/Ranker with Transformers:

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

pipe = pipeline("text-generation", model="PaSaMaster/Ranker")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PaSaMaster/Ranker")
model = AutoModelForCausalLM.from_pretrained("PaSaMaster/Ranker", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PaSaMaster/Ranker with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PaSaMaster/Ranker"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PaSaMaster/Ranker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PaSaMaster/Ranker

SGLang

How to use PaSaMaster/Ranker 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 "PaSaMaster/Ranker" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PaSaMaster/Ranker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "PaSaMaster/Ranker" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PaSaMaster/Ranker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PaSaMaster/Ranker with Docker Model Runner:
```
docker model run hf.co/PaSaMaster/Ranker
```

yuwendu commited on Sep 3

Commit

6c595b0

verified ·

1 Parent(s): ae88a79

Add baseline comparisons to PaSaMaster results

Browse files

Files changed (1) hide show

README.md +13 -8

README.md CHANGED Viewed

@@ -29,13 +29,19 @@ This design ranks authentic, traceable paper records instead of generating citat
 The following are **end-to-end PaSaMaster system results using this Ranker**, measured on PaSaMaster-Bench (244 expert-curated tasks across 38 disciplines):
-| Metric | Score |
-|---|---:|
-| NDCG@20 | **39.52** |
-| Recall@20 | **33.24** |
-| Precision@20 | **23.46** |
-| F1@20 | **23.00** |
-| Source hallucination | **0%** |
 PaSaMaster achieves **16.5×** the F1@20 of Google Scholar and **37.8% higher** F1@20 than GPT-5.2 in the reported evaluation, at approximately **$0.05 per query**.
@@ -48,4 +54,3 @@ Use this checkpoint within the PaSaMaster pipeline or a compatible evidence-grou
 - [Paper](https://arxiv.org/abs/2605.14306)
 - [Code](https://github.com/sjtu-sai-agents/PaSaMaster)
 - [PaSaMaster-Bench](https://huggingface.co/datasets/PaSaMaster/PaSaMaster_bench)

 The following are **end-to-end PaSaMaster system results using this Ranker**, measured on PaSaMaster-Bench (244 expert-curated tasks across 38 disciplines):
+| Method | NDCG@20 | Recall@20 | Precision@20 | F1@20 | Hallucination | Cost/query |
+|---|---:|---:|---:|---:|---:|---:|
+| Google Scholar | 2.07 | 1.69 | 1.48 | 1.39 | 0% | — |
+| OpenScholar | 14.61 | 11.68 | 8.52 | 7.92 | 0% | — |
+| Bohrium Science Navigator | 22.39 | 19.37 | 12.50 | 12.26 | 0% | — |
+| DeepSeek-v3.2 | 35.82 | 24.76 | 15.35 | 15.56 | 12.94% | $0.28 |
+| Kimi-K2.5 | 37.80 | 28.08 | 16.95 | 17.36 | 26.59% | $0.16 |
+| MiniMax-M2.7 | 30.70 | 24.23 | 14.42 | 15.11 | 32.66% | $0.18 |
+| GLM-5 | 35.89 | 28.99 | 16.93 | 18.18 | 21.64% | $0.56 |
+| Gemini-3.1-pro | 31.34 | 21.30 | 11.68 | 12.48 | 27.54% | $0.38 |
+| GPT-5.2 | 31.59 | 25.32 | 16.82 | 16.69 | 5.65% | $6.06 |
+| Google Scholar Labs | 30.54 | 29.01 | 18.79 | 18.87 | 0% | — |
+| **PaSaMaster** | **39.52** | **33.24** | **23.46** | **23.00** | **0%** | **$0.05** |
 PaSaMaster achieves **16.5×** the F1@20 of Google Scholar and **37.8% higher** F1@20 than GPT-5.2 in the reported evaluation, at approximately **$0.05 per query**.
 - [Paper](https://arxiv.org/abs/2605.14306)
 - [Code](https://github.com/sjtu-sai-agents/PaSaMaster)
 - [PaSaMaster-Bench](https://huggingface.co/datasets/PaSaMaster/PaSaMaster_bench)