Instructions to use tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter")

Transformers

How to use tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter

SGLang

How to use tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter",
    max_seq_length=2048,
)

Docker Model Runner
How to use tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter with Docker Model Runner:
```
docker model run hf.co/tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter
```

Egyptian Ministry English MCQ Generator (LoRA Adapter)

This repository contains a LoRA adapter fine-tuned on Qwen2.5-3B-Instruct for generating English multiple-choice questions following the style of the Egyptian Ministry of Education (General Secondary Stage).

Base Model

Model: unsloth/Qwen2.5-3B-Instruct
Fine-tuning Method: LoRA (PEFT)
Framework: Unsloth + TRL

Task

The adapter is trained to generate ministry-style English examination questions, including:

Grammar
Vocabulary
Unit-based questions
Topic-based questions

The generated output follows a structured JSON format.

Example:

{
  "questions": [
    {
      "statement": "...",
      "correct_answer": "...",
      "plausible_distractors": [
        "...",
        "...",
        "..."
      ],
      "explanation": "..."
    }
  ]
}

Training Data

The adapter was trained on a synthetic dataset derived from the Egyptian secondary English curriculum.

The dataset contains prompts covering:

Grammar Focus
Vocabulary
Topics
Units
Curriculum metadata
Official Ministry-style multiple-choice questions

Training Configuration

Base Model: Qwen2.5-3B-Instruct
LoRA Rank: 16
LoRA Alpha: 32
LoRA Dropout: 0.05
Sequence Length: 2048
Optimizer: AdamW 8-bit
Learning Rate: 1e-4

Usage

from unsloth import FastLanguageModel
from peft import PeftModel

model, 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)

Intended Use

This adapter is designed for:

Educational applications
Automatic English exam generation
Ministry-style assessment generation
Question authoring assistants

It is not intended for general-purpose chat or reasoning tasks.

Downloads last month: 67

Model tree for tokhey/egyptian-mcq-generator-qwen-2.5-3b-adapter

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

unsloth/Qwen2.5-3B-Instruct

Adapter

(476)

this model