Instructions to use madImad/questcrafter-distilgpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use madImad/questcrafter-distilgpt2 with Transformers:

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

pipe = pipeline("text-generation", model="madImad/questcrafter-distilgpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("madImad/questcrafter-distilgpt2")
model = AutoModelForCausalLM.from_pretrained("madImad/questcrafter-distilgpt2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use madImad/questcrafter-distilgpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "madImad/questcrafter-distilgpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "madImad/questcrafter-distilgpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/madImad/questcrafter-distilgpt2

SGLang

How to use madImad/questcrafter-distilgpt2 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 "madImad/questcrafter-distilgpt2" \
    --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": "madImad/questcrafter-distilgpt2",
		"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 "madImad/questcrafter-distilgpt2" \
        --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": "madImad/questcrafter-distilgpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use madImad/questcrafter-distilgpt2 with Docker Model Runner:
```
docker model run hf.co/madImad/questcrafter-distilgpt2
```

🧙 QuestCrafter — Instruction-Tuned distilgpt2 (TinyStories) 📌 Overview

QuestCrafter is a fine-tuned version of distilgpt2 trained on a structured fantasy quest dataset derived from TinyStories.

The model generates short RPG-style quests conditioned on structured control tokens:

<LEVEL=X>

<SETTING=...>

<TONE=...>

<LENGTH=...>

This project was developed as part of the MSc AI Machine Learning course.

🗂 Dataset

Base dataset: TinyStories (Hugging Face)

We reformatted the dataset into an instruction-style supervised format:

<LEVEL=3> <SETTING=forest> <TONE=dark> <LENGTH=short>

Instruction:

Create a quest involving betrayal.

Response:

...

Train/Validation/Test split: 80/10/10.

🏗 Training Setup

Base model: distilgpt2

Framework: PyTorch + Hugging Face Transformers

Epochs: 3

Learning rate: 5e-5

Batch size: 8

Max length: 256

Mixed precision (fp16) enabled on GPU

🎮 Controllability

The model supports structured control tokens:

Level (1–10)

Setting (forest, desert city, medieval town, etc.)

Tone (epic, dark, humorous)

Length (short / medium)

This enables conditional generation and improved prompt-faithfulness compared to baseline distilgpt2.

📊 Evaluation

We compared baseline distilgpt2 vs fine-tuned model on a fixed test set of 50 prompts.

Metrics used:

Validation loss

Perplexity

Distinct-2 (diversity metric)

Human evaluation rubric (1–5 scale):

Coherence

Prompt-faithfulness

Creativity

The fine-tuned model showed:

Lower perplexity

Higher prompt-faithfulness

Improved structural consistency

🛡 Safety

A lightweight keyword-based safety filter is applied during generation to prevent harmful or inappropriate content. Unsafe generations are automatically regenerated.

⚠️ Limitations

May occasionally ignore control tokens

May produce repetitive text for long outputs

Not trained for real-world advisory use

Fantasy-only domain

🎓 Academic Context

This model was developed for the QuestCrafter AI project (MSc AI). It demonstrates:

Instruction-style fine-tuning

Controlled generation

Baseline vs tuned comparison

Structured evaluation pipeline

Downloads last month: 11

Safetensors

Model size

81.9M params

Tensor type

F32

Model tree for madImad/questcrafter-distilgpt2

Base model

distilbert/distilgpt2

Finetuned

(1535)

this model

madImad
/

questcrafter-distilgpt2

Instruction:

Response:

Model tree for madImad/questcrafter-distilgpt2

Dataset used to train madImad/questcrafter-distilgpt2