GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
tokhey
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
tokhey
Model Tree
unsloth/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
unsloth/Qwen2.5-3B-InstructThe adapter is trained to generate ministry-style English examination questions, including:
The generated output follows a structured JSON format.
Example:
json
{"questions": [{"statement": "...","correct_answer": "...","plausible_distractors": ["...","...","..."],"explanation": "..."}]}
The adapter was trained on a synthetic dataset derived from the Egyptian secondary English curriculum.
The dataset contains prompts covering:
python
from unsloth import FastLanguageModelfrom peft import PeftModelmodel, tokenizer = FastLanguageModel.from_pretrained("unsloth/Qwen2.5-3B-Instruct",max_seq_length=2048,)model = PeftModel.from_pretrained(model,"tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter",)FastLanguageModel.for_inference(model)
This adapter is designed for:
It is not intended for general-purpose chat or reasoning tasks.