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 commited on Apr 5

Commit

a8f2981

1 Parent(s): 65c52b2

fix: remove Google Drive mount (Colab-only) - use Kaggle output + GitHub push instead

Browse files

- Removed google.colab dependency (doesn't work on Kaggle)
- Added GitHub push cell to save model permanently
- Added warning to download outputs before session expires
- Kaggle-compatible now

Files changed (1) hide show

kaggle_train_stack29_v5.ipynb +60 -14

kaggle_train_stack29_v5.ipynb CHANGED Viewed

@@ -52,15 +52,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Mount Google Drive to save outputs permanently\n",
-    "from google.colab import drive\n",
-    "drive.mount('/content/drive')\n",
     "\n",
-    "# Create permanent output directory in Google Drive\n",
-    "DRIVE_OUTPUT_DIR = '/content/drive/MyDrive/stack-2.9-output'\n",
-    "os.makedirs(DRIVE_OUTPUT_DIR, exist_ok=True)\n",
     "\n",
-    "print(f\"\u2705 Google Drive mounted: {DRIVE_OUTPUT_DIR}\")\n"
    ]
   },
   {
@@ -213,16 +213,62 @@
     "print(f'Merged model: {merged_dir}')\n",
     "!ls -lh {merged_dir}\n",
     "\n",
-    "# Copy merged model to Google Drive\n",
     "import shutil\n",
-    "drive_merge_dir = os.path.join(DRIVE_OUTPUT_DIR, 'merged')\n",
     "if os.path.exists(merged_dir):\n",
-    "    if os.path.exists(drive_merge_dir):\n",
-    "        shutil.rmtree(drive_merge_dir)\n",
-    "    shutil.copytree(merged_dir, drive_merge_dir)\n",
-    "    print(f\"\u2705 Model copied to Google Drive: {drive_merge_dir}\")\n",
     "else:\n",
-    "    print(\"\u26a0\ufe0f Merged model not found, skipping Drive copy\")\n"
    ]
   },
   {

    "metadata": {},
    "outputs": [],
    "source": [
+    "# Save to Kaggle output (download before session ends!)\n",
+    "# Kaggle sessions expire after 9 hours - download outputs immediately!\n",
     "\n",
+    "# Create a symbolic link to make paths easier\n",
+    "OUTPUT_DIR = os.path.join(REPO_DIR, 'training_output')\n",
+    "os.makedirs(OUTPUT_DIR, exist_ok=True)\n",
     "\n",
+    "print(f\"\u2705 Output directory: {OUTPUT_DIR}\")\n",
+    "print(\"\u26a0\ufe0f IMPORTANT: Download outputs from 'Output' tab before session expires!\")\n"
    ]
   },
   {
     "print(f'Merged model: {merged_dir}')\n",
     "!ls -lh {merged_dir}\n",
     "\n",
+    "print(\"\\n\u26a0\ufe0f DOWNLOAD THE MODEL NOW: Go to Output tab and download 'merged' folder!\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Push merged model to GitHub LFS (optional - for permanent storage)\n",
+    "# This saves the model to your GitHub repo so you can download anytime\n",
+    "\n",
+    "# Configure Git LFS\n",
+    "!git lfs install 2>/dev/null || echo 'Git LFS already installed'\n",
+    "\n",
+    "# Clone the repo if not already there\n",
+    "import subprocess\n",
+    "repo_url = 'https://github.com/my-ai-stack/stack-2.9.git'\n",
+    "local_repo = '/kaggle/working/stack-2.9-repo'\n",
+    "\n",
+    "if not os.path.exists(local_repo):\n",
+    "    subprocess.run(['git', 'clone', repo_url, local_repo], check=True)\n",
+    "\n",
+    "# Copy merged model to repo\n",
     "import shutil\n",
+    "target_dir = os.path.join(local_repo, 'models/stack-2.9-finetuned')\n",
+    "os.makedirs(target_dir, exist_ok=True)\n",
+    "\n",
     "if os.path.exists(merged_dir):\n",
+    "    # Copy files\n",
+    "    for f in os.listdir(merged_dir):\n",
+    "        src = os.path.join(merged_dir, f)\n",
+    "        dst = os.path.join(target_dir, f)\n",
+    "        if os.path.isdir(src):\n",
+    "            shutil.copytree(src, dst, dirs_exist_ok=True)\n",
+    "        else:\n",
+    "            shutil.copy2(src, dst)\n",
+    "    \n",
+    "    print(f'\u2705 Copied model to {target_dir}')\n",
+    "    \n",
+    "    # Push to GitHub\n",
+    "    os.chdir(local_repo)\n",
+    "    subprocess.run(['git', 'add', 'models/stack-2.9-finetuned/'], check=True)\n",
+    "    subprocess.run(['git', 'config', 'user.email', 'kaggle@kaggle.com'], check=True)\n",
+    "    subprocess.run(['git', 'config', 'user.name', 'Kaggle Auto-Push'], check=True)\n",
+    "    subprocess.run(['git', 'commit', '-m', 'feat: add fine-tuned model from Kaggle'], check=True)\n",
+    "    \n",
+    "    # Push (you may need a GitHub token for private repos)\n",
+    "    result = subprocess.run(['git', 'push', 'origin', 'main'], capture_output=True, text=True)\n",
+    "    if result.returncode == 0:\n",
+    "        print('\u2705 Model pushed to GitHub!')\n",
+    "    else:\n",
+    "        print(f'\u26a0\ufe0f Push failed: {result.stderr}')\n",
+    "        print('   You can still download from Kaggle Output tab.')\n",
     "else:\n",
+    "    print('\u26a0\ufe0f Merged model not found. Train first!')\n"
    ]
   },
   {