Instructions to use ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt with Transformers:

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

pipe = pipeline("text-generation", model="ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt")
model = AutoModelForCausalLM.from_pretrained("ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt

SGLang

How to use ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt 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 "ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt" \
    --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": "ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt",
		"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 "ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt" \
        --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": "ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt with Docker Model Runner:
```
docker model run hf.co/ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt
```

pyfccc commited on Feb 22

Commit

8051a90

verified ·

1 Parent(s): 0efcb0d

Restore README

Browse files

Files changed (1) hide show

README.md +29 -52

README.md CHANGED Viewed

@@ -1,69 +1,46 @@
 ---
-base_model: google/gemma-2-2b-it
 library_name: transformers
-model_name: seed3
 tags:
-- generated_from_trainer
-- trl
-- dpo
-licence: license
 ---
-# Model Card for seed3
-This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-## Quick start
-```python
-from transformers import pipeline
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/pppp4-carnegie-mellon-university/dpo_verify1/runs/28tomuqy)
-This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
-### Framework versions
-- TRL: 0.27.0
-- Transformers: 4.57.1
-- Pytorch: 2.8.0
-- Datasets: 4.1.1
-- Tokenizers: 0.22.1
-## Citations
-Cite DPO as:
-```bibtex
-@inproceedings{rafailov2023direct,
-    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
-    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
-    year         = 2023,
-    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
-    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
-    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
-}
-```
-Cite TRL as:
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```

 ---
 library_name: transformers
+pipeline_tag: text-generation
 tags:
+- alignment
+- evaluation
+- preference-learning
+- ripd
+base_model: google/gemma-2-2b-it
+datasets:
+- ZDCSlab/ripd-dataset
 ---
+# ZDCSlab/ripd-ultra-real-gemma2-2b-it-seed-bt
+This checkpoint is part of the artifact release for
+**“Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges.”**
+It is a policy model trained under a specific rubric condition to study how evaluation-time preference drift propagates into downstream alignment.
+---
+## Configuration
+- **Setting:** ultra-real
+- **Base model:** [Gemma-2-2B-it](https://huggingface.co/google/gemma-2-2b-it)
+- **Label condition:** seed
+- **Training data:** Bench + Target (mixed)
+- **Objective:** Direct Preference Optimization (DPO)
+The `seed` condition corresponds to preference labels generated by an LLM judge under the `seed` rubric variant.
+---
+## Intended Use
+This model is released for research on evaluation-time robustness, preference drift, and alignment propagation.
+It is not intended for production deployment.
+---
+## Resources
+- 📄 Paper: https://www.arxiv.org/pdf/2602.13576
+- 💻 Code & Evaluation Pipeline: https://github.com/ZDCSlab/Rubrics-as-an-Attack-Surface
+- 📊 Dataset: https://huggingface.co/datasets/ZDCSlab/ripd-dataset