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")
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

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 / stack /training /run_local.sh

walidsobhie-code

refactor: Squeeze folders further - cleaner structure

65888d5 about 1 month ago

raw

history blame contribute delete

1.4 kB

	#!/bin/bash
	# Stack 2.9 Local Training Setup Script

	set -e

	cd /Users/walidsobhi/.openclaw/workspace/stack-2.9

	echo "=== Step 1: Verify venv ==="
	source .venv/bin/activate
	python -c "import torch; print('PyTorch:', torch.__version__)"
	echo "MPS available: $(python -c 'import torch; print(torch.backends.mps.is_available())')"

	echo ""
	echo "=== Step 2: Export Qwen model from Ollama ==="
	# This creates ./base_model_qwen7b from Ollama
	mkdir -p ./base_model_qwen7b
	ollama cp qwen2.5-coder:7b qwen2.5-coder:7b-local
	# Export won't work directly, so we'll download from HF instead

	echo ""
	echo "=== Step 3: Download model from HuggingFace ==="
	python -c "
	from transformers import AutoModelForCausalLM, AutoTokenizer
	print('Downloading Qwen2.5-Coder-7B...')
	tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen2.5-Coder-7B', trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained('Qwen/Qwen2.5-Coder-7B', trust_remote_code=True)
	tokenizer.save_pretrained('./base_model_qwen7b')
	model.save_pretrained('./base_model_qwen7b')
	print('Model saved to ./base_model_qwen7b')
	"

	echo ""
	echo "=== Step 4: Prepare dataset ==="
	# Convert JSONL to training format
	python stack-2.9-training/prepare_dataset.py --input training-data/generated/synthetic_50k.jsonl

	echo ""
	echo "=== Step 5: Run training ==="
	python stack-2.9-training/train_lora.py --config stack-2.9-training/train_config_local.yaml