GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ChatoyantAI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ChatoyantAI
Model Tree
google/gemma-4-12B-it
Input Modalities
Output Modalities
Supported Functionality
The 75:25 ratio is by sample count.
python
from transformers import AutoProcessor, Gemma4UnifiedForConditionalGenerationfrom peft import PeftModel base_id = "google/gemma-4-12B-it"adapter_id = "ChatoyantAI/Gemma-4-12B-Roleplay-7525-SFT"processor = AutoProcessor.from_pretrained(adapter_id)base = Gemma4UnifiedForConditionalGeneration.from_pretrained( base_id, dtype="auto", device_map="auto")model = PeftModel.from_pretrained(base, adapter_id)This repository contains the LoRA adapter, tokenizer and Gemma chat template. It is not a standalone merged base model. Use a Transformers/PEFT version with Gemma 4 Unified support and keep the included template.
Training data, optimizer states and private logs are not included.