Instructions to use art87able/unstuck-qwen2.5-0.5b-steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use art87able/unstuck-qwen2.5-0.5b-steps with Transformers:

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

pipe = pipeline("text-generation", model="art87able/unstuck-qwen2.5-0.5b-steps")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("art87able/unstuck-qwen2.5-0.5b-steps")
model = AutoModelForMultimodalLM.from_pretrained("art87able/unstuck-qwen2.5-0.5b-steps")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use art87able/unstuck-qwen2.5-0.5b-steps with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "art87able/unstuck-qwen2.5-0.5b-steps"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "art87able/unstuck-qwen2.5-0.5b-steps",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/art87able/unstuck-qwen2.5-0.5b-steps

SGLang

How to use art87able/unstuck-qwen2.5-0.5b-steps 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 "art87able/unstuck-qwen2.5-0.5b-steps" \
    --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": "art87able/unstuck-qwen2.5-0.5b-steps",
		"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 "art87able/unstuck-qwen2.5-0.5b-steps" \
        --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": "art87able/unstuck-qwen2.5-0.5b-steps",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use art87able/unstuck-qwen2.5-0.5b-steps with Docker Model Runner:
```
docker model run hf.co/art87able/unstuck-qwen2.5-0.5b-steps
```

Unstuck — Qwen2.5-0.5B fine-tuned for ADHD task breakdowns

A tiny (0.5B) instruct model fine-tuned to turn one overwhelming task into tiny, timed, categorised steps in the exact JSON schema used by Unstuck (HF Build Small Hackathon, Backyard AI track).

It powers Unstuck's UNSTUCK_BACKEND=finetuned path — a fully local, serverless-free option that runs the same generate(prompt) -> str seam as the app's other backends.

What it does

Given an overwhelming task, it returns only:

{"steps":[{"text":"Open a trash bag and collect visible rubbish","category":"admin","est_minutes":5}, ...]}

each step a single concrete action starting with an imperative verb,
one category from admin · creative · errand · deep-work,
a positive-integer minute estimate, never above 25 (a hard app rule).

How it was built

Base: Qwen/Qwen2.5-0.5B-Instruct.
Data: 130 schema-valid breakdowns distilled from a strong serverless model (Qwen/Qwen3-30B-A3B-Instruct-2507 on Nebius Token Factory), each filtered through Unstuck's own validator so only on-contract examples survive. Purely synthetic — no user data.
Method: LoRA (r=16, α=32, dropout 0.05; q/k/v/o projections), 3 epochs, lr 2e-4, merged into the base. Final train loss ≈ 0.21.
Compute: a single Modal A10G GPU. Full pipeline (distill → train → verify): scripts/finetune/.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("art87able/unstuck-qwen2.5-0.5b-steps")
model = AutoModelForCausalLM.from_pretrained("art87able/unstuck-qwen2.5-0.5b-steps")
# Feed it Unstuck's breakdown prompt (see unstuck.prompts.breakdown_prompt) and parse the JSON.

Or in the app: UNSTUCK_BACKEND=finetuned python app.py.

Limitations

A 0.5B model specialised for one narrow JSON task — it is not a general chat model. Outputs should still be schema-validated (the app does one repair retry on failure). Estimates are starting points; Unstuck recalibrates them to your real timings client-side.