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
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Every saved training step is a separate git revision. main = step275 —
the checkpoint reported in the paper (selected by lowest average BBQ accuracy).
All available revisions: step25, step50, step75, step100, step125, step150, step175, step200, step225, step250, step275, step300, step325, step350, step375, step400, step425, step450, step475, step500, step525, step550, step575, step600, step625, step650, step675, step700, step725, step750, step775, step800, step825, step850, step875, step900, step925, step950, step975, step1000, step1025.
python
from transformers import AutoModelForCausalLMfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")model = PeftModel.from_pretrained(base, "MichiganNLP/Qwen2.5-7B-Instruct-bias-z12-Age-lora", revision="step275")Qwen/Qwen2.5-7B-Instructmain revision: step275, the step reported in the paper.Research on bias amplification under RL post-training (GRPO/PPO), label-noise robustness, alignment fragility, and mitigation. Not for deployment or for producing biased or harmful content.
from transformers import AutoModelForCausalLMfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")model = PeftModel.from_pretrained(base, "MichiganNLP/Qwen2.5-7B-Instruct-bias-z12-Age-lora", revision="step275")