Instructions to use alexyang790/gpt2-classbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alexyang790/gpt2-classbot with Transformers:

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

pipe = pipeline("text-generation", model="alexyang790/gpt2-classbot")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alexyang790/gpt2-classbot")
model = AutoModelForCausalLM.from_pretrained("alexyang790/gpt2-classbot", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alexyang790/gpt2-classbot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alexyang790/gpt2-classbot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexyang790/gpt2-classbot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alexyang790/gpt2-classbot

SGLang

How to use alexyang790/gpt2-classbot 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 "alexyang790/gpt2-classbot" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexyang790/gpt2-classbot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "alexyang790/gpt2-classbot" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexyang790/gpt2-classbot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alexyang790/gpt2-classbot with Docker Model Runner:
```
docker model run hf.co/alexyang790/gpt2-classbot
```

language: en tags: - gpt2 - text-generation - class-scheduling - fine-tuned license: mit datasets: web-scrapped dataset from Louslist.org with a custom API model-index: - name: GPT-2 UVA Class Scheduler

🧠 GPT-2 UVA Class Scheduler (Fine-Tuned)

This model is a fine-tuned version of gpt2 on a custom dataset extracted from Lou's List — the University of Virginia's course directory. It is designed to answer questions about course offerings, availability, instructors, and generate plausible class schedules in natural language.

🔍 Use Cases

Ask for available classes in a subject
Query instructors teaching specific courses
Get summaries of course descriptions
Generate sample schedules for a semester

🚀 Example Usage

from transformers import GPT2LMHeadModel, GPT2Tokenizer

model = GPT2LMHeadModel.from_pretrained("your-username/uva-gpt2-scheduler")
tokenizer = GPT2Tokenizer.from_pretrained("your-username/uva-gpt2-scheduler")

prompt = "What classes are available for Data Science in Spring 2024?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

🏋️ Training

Base model: gpt2 (117M parameters)
Dataset: Custom dataset scraped and cleaned from UVA's Lou’s List
Training platform: Google Colab
Epochs: 3
Batch size: 4
Learning rate: 5e-5
Tokenizer: GPT-2 tokenizer
Token Length: 128

📁 Model Files

pytorch_model.bin: Model weights
config.json: Model configuration
tokenizer.json, vocab.json, merges.txt: Tokenizer files

🧪 Limitations

The model is trained only on course listing data, so it may hallucinate responses if prompted with unrelated queries.
Class availability and schedules may change over time — this model reflects a snapshot of the data at the time of training.

📜 License

MIT License

🙏 Acknowledgements

Course data provided via Lou’s List (https://louslist.org)
Fine-tuning done for the [Class Project Name] at the University of Virginia M.S. in Data Science

Downloads last month: 12

Safetensors

Model size

0.1B params

Tensor type

F32

alexyang790
/

gpt2-classbot