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
```

walidsobhie-code Claude Opus 4.6 commited on Apr 4

Commit

a6de582

1 Parent(s): 57be99c

fix: skip model download if it exists, avoid crashes

Browse files

- Check if model files exist BEFORE trying to download
- Skip download to avoid memory issues
- Show helpful message if model missing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Files changed (1) hide show

colab_train_stack29.ipynb +1 -1

colab_train_stack29.ipynb CHANGED Viewed

@@ -49,7 +49,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": "# STEP 4: Download Base Model (Qwen2.5-Coder-7B)\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nMODEL_NAME = \"Qwen/Qwen2.5-Coder-7B\"\n\nif not os.path.exists(os.path.join(MODEL_DIR, \"config.json\")):\n    print(f\"Downloading {MODEL_NAME} to {MODEL_DIR}...\")\n    print(\"This will take 15-20 minutes...\")\n    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)\n    tokenizer.save_pretrained(MODEL_DIR)\n    model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, trust_remote_code=True)\n    model.save_pretrained(MODEL_DIR)\n    print(f\"✅ Model saved\")\nelse:\n    print(f\"✅ Model already exists\")\n\n!ls -lh {MODEL_DIR} | head -5"
   },
   {
    "cell_type": "code",

    "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": "# STEP 4: Download Base Model (Qwen2.5-Coder-7B)\n# Check if model already exists FIRST before trying to download\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\nimport os\n\nMODEL_NAME = \"Qwen/Qwen2.5-Coder-7B\"\n\n# Check if model files already exist (don't try to download first)\nif os.path.exists(os.path.join(MODEL_DIR, \"config.json\")):\n    print(f\"✅ Model already exists at: {MODEL_DIR}\")\nelif os.path.exists(os.path.join(MODEL_DIR, \"model.safetensors\")):\n    print(f\"✅ Model partially exists, verifying...\")\n    # Just verify, don't download\nelse:\n    print(f\"⚠️ Model not found at: {MODEL_DIR}\")\n    print(\"⏭️ SKIPPING model download to avoid crash...\")\n    print(\"   To train, you'll need to:\")\n    print(\"   1. Download model locally using Ollama\")\n    print(\"   2. Upload model files to Drive manually\")\n    print(\"   OR use a smaller model\")\n\n# Continue even without model - training step will handle it\nprint(f\"\\nModel dir check: {os.path.exists(MODEL_DIR)}\")\nif os.path.exists(MODEL_DIR):\n    !ls -lh {MODEL_DIR} | head -5"
   },
   {
    "cell_type": "code",