Instructions to use my-ai-stack/Stack-2-9-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use my-ai-stack/Stack-2-9-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="my-ai-stack/Stack-2-9-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("my-ai-stack/Stack-2-9-finetuned")
model = AutoModelForCausalLM.from_pretrained("my-ai-stack/Stack-2-9-finetuned", device_map="auto")
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 my-ai-stack/Stack-2-9-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "my-ai-stack/Stack-2-9-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "my-ai-stack/Stack-2-9-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/my-ai-stack/Stack-2-9-finetuned

SGLang

How to use my-ai-stack/Stack-2-9-finetuned 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 "my-ai-stack/Stack-2-9-finetuned" \
    --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": "my-ai-stack/Stack-2-9-finetuned",
		"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 "my-ai-stack/Stack-2-9-finetuned" \
        --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": "my-ai-stack/Stack-2-9-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use my-ai-stack/Stack-2-9-finetuned with Docker Model Runner:
```
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
```

Stack-2-9-finetuned / docs /LAUNCH_CHECKLIST.md

walidsobhie-code

reorganize: consolidate root level to 20 folders

b8e3e42 4 months ago

preview code

Raw

History Blame Contribute Delete

3.24 kB

Stack 2.9 Official Launch Checklist

This document outlines the steps to officially launch Stack 2.9.

Phase 1: Testing & Validation

✅ 1.1 Run Unit Tests

cd stack-2.9
python -m pytest samples/ -v

✅ 1.2 Test Model Inference

# Test with Ollama (local)
python stack/eval/simple_test.py

# Or test with OpenAI
python stack/eval/simple_test.py --provider openai

⏳ 1.3 Run Benchmarks (Required)

# Download datasets
python scripts/download_benchmark_datasets.py

# Run HumanEval
python stack/eval/run_proper_evaluation.py --benchmark humaneval --output results/

# Run MBPP
python stack/eval/run_proper_evaluation.py --benchmark mbpp --output results/

⏳ 1.4 Test Deployment

# Test Docker locally
cd stack/deploy
docker build -t stack-2.9 .
docker run -p 8000:8000 stack-2.9

Phase 2: Model Preparation

⏳ 2.1 Fine-tune Model

# Option 1: Together AI (free credits)
python stack/training/together_finetune.py --model 7b --data data/final/train.jsonl

# Option 2: Google Colab
# Open colab_train_stack29.ipynb

⏳ 2.2 Quantize Model (for deployment)

python stack/training/quantize_awq.py \
    --model Qwen/Qwen2.5-Coder-7B \
    --output stack/deploy/models/

⏳ 2.3 Upload to HuggingFace

python -c "
from huggingface_hub import HfApi
api = HfApi()
api.upload_folder(
    folder_path='./stack/deploy/models',
    repo_id='yourusername/stack-2.9-7b',
    repo_type='model'
)
"

Phase 3: Deployment

⏳ 3.1 Deploy to HuggingFace Spaces (Free)

# 1. Create space: https://huggingface.co/spaces/new
# 2. Choose: Docker, Python 3.11
# 3. Push files:
git clone https://huggingface.co/spaces/yourusername/stack-2.9
cp stack/deploy/hfSpaces/* .
git add . && git push

⏳ 3.2 Create Demo UI (Gradio)

# Already included in hfSpaces/app.py
# Access at: https://your-space.hf.space

Phase 4: Documentation & Launch

⏳ 4.1 Final Documentation Check

README.md complete
FREE_DEPLOYMENT.md complete
API documentation in stack/docs/
Examples in samples/

⏳ 4.2 Create Release

# Tag the release
git tag v1.0.0
git push origin v1.0.0

# Create GitHub release with:
# - Release notes
# - Model download links
# - Demo links

⏳ 4.3 Submit to Platforms

Submit to OpenRouter (API listing)
Submit to HuggingFace (model + Space)
Add to LangChain integrations (optional)

Phase 5: Promotion

⏳ 5.1 Social Media

Announce on Twitter/X
Post on LinkedIn
Share on AI Discord servers

⏳ 5.2 Community

Create Discord server
Add to awesome lists
Submit to Product Hunt

Quick Start (If Everything Ready)

# 1. Test locally
python stack/eval/simple_test.py

# 2. Deploy to HF Spaces
# (manual - see Phase 3)

# 3. Create release
git tag v1.0.0 && git push origin v1.0.0

Current Status

Item	Status
Unit Tests	✅ Ready (in samples/)
Inference Test	✅ Ready
Benchmarks	⏳ Need to run
Model Fine-tuned	⏳ Need to do
Deployment	⏳ Need to deploy
Release	⏳ Need to create