GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
yavuz-ai
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
yavuz-ai
Model Tree
Base
yavuz-ai/qwen3-4b-cai-sft
Adapter
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
This stage pushes over-refusal on benign prompts to 0.484 (safety ~1.0). It reproduces the harmless-vs-overrefusal regression; see the repo and the benign-mix variant (qwen3-4b-cai-rlaif-v2) that partially recovers it.
LoRA DPO (TRL), r=16/alpha=32, beta 0.1, 1 epoch, on ~1,777 both-orders-agreed preference pairs. Reference = the adapter-disabled SL-CAI model (RL-CAI starts from the SL-CAI model).
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("yavuz-ai/qwen3-4b-cai-sft")model = PeftModel.from_pretrained(base, "yavuz-ai/qwen3-4b-cai-rlaif")tok = AutoTokenizer.from_pretrained("yavuz-ai/qwen3-4b-cai-sft")