GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MichiganNLP
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
MichiganNLP
Model Tree
google/gemma-2-9b
Input Modalities
Output Modalities
Supported Functionality
Every GRPO step is a git revision. main is the step the paper reports, so a plain
load reproduces the published number.
| Revision | |
|---|---|
step50 | the checkpoint reported in the paper (= main) |
step100 |
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b", torch_dtype="bfloat16")tok = AutoTokenizer.from_pretrained("google/gemma-2-9b")# main == step50, the checkpoint reported in the papermodel = PeftModel.from_pretrained(base, "MichiganNLP/hacking-fairness-benchmarks-gemma-2-9b-z1")# or pick any other stepmodel = PeftModel.from_pretrained(base, "MichiganNLP/hacking-fairness-benchmarks-gemma-2-9b-z1", revision="step100")
The model is prompted to answer in <think>...</think><answer>A</answer> format.
LoRA config: rank 32, alpha 32, on q,k,v,o,gate,up,down_proj.
Trained against base revision 33c193028431c2fde6c6e51f29e6f17b60cbfac6.
bibtex
@inproceedings{deng2026one,title = {One Example Is Enough to Pass Fairness Benchmarks:Rethinking Fairness Evaluation for Aligned {LLM}s},author = {Deng, Naihao and Arif, Samee and Chang, Shuaichen andChen, Yulong and Mihalcea, Rada},booktitle = {Proceedings of the 2026 Conference on Empirical Methods inNatural Language Processing},year = {2026}}