GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
IAmSkyDra
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
IAmSkyDra
Model Tree
unsloth/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
unsloth/Qwen3.5-9B32121.1012outputs/sft/qwen3_5_9b/checkpoint-3212python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "unsloth/Qwen3.5-9B"adapter = "IAmSkyDra/vitutor-qwen3-5-9b-sft-ckpt3212"tokenizer = AutoTokenizer.from_pretrained(adapter)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")model = PeftModel.from_pretrained(model, adapter)
This checkpoint is intended for research experiments on Vietnamese educational tutoring, especially checkpoint comparison and downstream alignment experiments. It is not a final safety-reviewed tutoring product.