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

6a2254e

1 Parent(s): 78417b9

fix: fix git clone command in Kaggle notebook

Browse files

- Use subprocess instead of shell command

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

Files changed (1) hide show

kaggle_train_stack29.ipynb +1 -228

kaggle_train_stack29.ipynb CHANGED Viewed

@@ -1,228 +1 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# 🚀 Stack 2.9 - Kaggle Training Notebook\n",
-    "\n",
-    "**Free GPU training on Kaggle**\n",
-    "\n",
-    "This notebook trains a LoRA adapter for Stack 2.9 on **Qwen2.5-Coder-7B** using Kaggle's free GPU.\n",
-    "\n",
-    "⏱️ **Expected runtime:** 2-4 hours\n",
-    "💾 **VRAM needed:** ~16GB (Kaggle P100 has 16GB)\n",
-    "\n",
-    "---\n",
-    "\n",
-    "**Instructions:**\n",
-    "1. Enable GPU: Settings → Accelerator → GPU P100\n",
-    "2. Run cells in order from the top\n",
-    "3. Model auto-downloads if not present\n",
-    "\n",
-    "---"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 1: Check GPU\n",
-    "!nvidia-smi"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 2: Clone repo\n",
-    "import os\n",
-    "import shutil\n",
-    "\n",
-    "REPO_DIR = \"/kaggle/working/stack-2.9\"\n",
-    "\n",
-    "if os.path.exists(REPO_DIR):\n",
-    "    shutil.rmtree(REPO_DIR)\n",
-    "\n",
-    "!git clone https://github.com/my-ai-stack/stack-2.9.git {REPO_DIR}\n",
-    "\n",
-    "os.chdir(REPO_DIR)\n",
-    "print(f\"✅ Working in: {os.getcwd()}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 3: Install dependencies\n",
-    "!pip install -q torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\n",
-    "!pip install -q transformers peft accelerate datasets pyyaml tqdm scipy bitsandbytes\n",
-    "print(\"✅ Dependencies installed\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 4: Setup paths (MODEL_DIR, OUTPUT_DIR)\n",
-    "import os\n",
-    "\n",
-    "REPO_DIR = \"/kaggle/working/stack-2.9\"\n",
-    "MODEL_DIR = os.path.join(REPO_DIR, \"base_model_qwen7b\")\n",
-    "OUTPUT_DIR = os.path.join(REPO_DIR, \"training_output\")\n",
-    "\n",
-    "print(f\"REPO_DIR: {REPO_DIR}\")\n",
-    "print(f\"MODEL_DIR: {MODEL_DIR}\")\n",
-    "print(f\"OUTPUT_DIR: {OUTPUT_DIR}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 5: Download model (if not exists)\n",
-    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
-    "\n",
-    "if os.path.exists(os.path.join(MODEL_DIR, \"config.json\")):\n",
-    "    print(\"✅ Model already exists, skipping download!\")\n",
-    "else:\n",
-    "    print(\"⬇️ Downloading model (Qwen2.5-Coder-7B)...\")\n",
-    "    print(\"This takes ~10-15 minutes...\")\n",
-    "    tokenizer = AutoTokenizer.from_pretrained(\"Qwen/Qwen2.5-Coder-7B\", trust_remote_code=True)\n",
-    "    tokenizer.save_pretrained(MODEL_DIR)\n",
-    "    model = AutoModelForCausalLM.from_pretrained(\"Qwen/Qwen2.5-Coder-7B\", trust_remote_code=True)\n",
-    "    model.save_pretrained(MODEL_DIR)\n",
-    "    print(\"✅ Model downloaded!\")\n",
-    "\n",
-    "!ls -lh {MODEL_DIR} | head -5"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 6: Create config\n",
-    "import yaml\n",
-    "import os\n",
-    "\n",
-    "os.makedirs(OUTPUT_DIR, exist_ok=True)\n",
-    "\n",
-    "config = {\n",
-    "    'model': {'name': MODEL_DIR, 'trust_remote_code': True, 'torch_dtype': 'float16'},\n",
-    "    'data': {'input_path': './data/final/train.jsonl', 'max_length': 2048},\n",
-    "    'lora': {'r': 16, 'alpha': 32, 'dropout': 0.05,\n",
-    "             'target_modules': ['q_proj', 'k_proj', 'v_proj', 'o_proj'],\n",
-    "             'bias': 'none', 'task_type': 'CAUSAL_LM'},\n",
-    "    'training': {'num_epochs': 1, 'batch_size': 2, 'gradient_accumulation': 4,\n",
-    "                 'learning_rate': 2e-4, 'warmup_steps': 50, 'weight_decay': 0.01,\n",
-    "                 'max_grad_norm': 1.0, 'logging_steps': 5, 'eval_steps': 100,\n",
-    "                 'save_steps': 200, 'save_total_limit': 2, 'fp16': True, 'bf16': False,\n",
-    "                 'gradient_checkpointing': True},\n",
-    "    'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'),\n",
-    "               'merged_dir': os.path.join(OUTPUT_DIR, 'merged')},\n",
-    "    'quantization': {'enabled': False},\n",
-    "    'hardware': {'device': 'cuda', 'num_gpus': 1, 'use_4bit': False, 'use_8bit': False}\n",
-    "}\n",
-    "\n",
-    "config_path = os.path.join(OUTPUT_DIR, \"train_config.yaml\")\n",
-    "with open(config_path, 'w') as f:\n",
-    "    yaml.dump(config, f)\n",
-    "\n",
-    "print(f\"✅ Config saved to: {config_path}\")\n",
-    "print(f\"   Device: {config['hardware']['device']}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 7: Train LoRA\n",
-    "import sys\n",
-    "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n",
-    "\n",
-    "print(\"=\"*60)\n",
-    "print(\"STARTING TRAINING\")\n",
-    "print(\"=\"*60)\n",
-    "\n",
-    "from train_lora import train_lora\n",
-    "trainer = train_lora(config_path)\n",
-    "\n",
-    "print(\"=\"*60)\n",
-    "print(\"TRAINING COMPLETED!\")\n",
-    "print(\"=\"*60)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 8: Merge model\n",
-    "import sys\n",
-    "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n",
-    "from merge_adapter import merge_adapter\n",
-    "\n",
-    "merged_dir = os.path.join(OUTPUT_DIR, \"merged\")\n",
-    "os.makedirs(merged_dir, exist_ok=True)\n",
-    "\n",
-    "merge_config = {\n",
-    "    'model': {'name': MODEL_DIR, 'trust_remote_code': True},\n",
-    "    'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'), 'merged_dir': merged_dir},\n",
-    "    'quantization': {'enabled': False}\n",
-    "}\n",
-    "\n",
-    "merge_cfg_path = os.path.join(OUTPUT_DIR, \"merge_config.yaml\")\n",
-    "with open(merge_cfg_path, 'w') as f:\n",
-    "    yaml.dump(merge_config, f)\n",
-    "\n",
-    "merge_adapter(merge_cfg_path, os.path.join(OUTPUT_DIR, \"lora\"), merged_dir)\n",
-    "\n",
-    "print(f\"✅ Merged model saved to: {merged_dir}\")\n",
-    "!ls -lh {merged_dir}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# STEP 9: Done!\n",
-    "print(\"=\"*60)\n",
-    "print(\"🎉 TRAINING COMPLETE!\")\n",
-    "print(\"=\"*60)\n",
-    "print(f\"LoRA adapter: {os.path.join(OUTPUT_DIR, 'lora')}\")\n",
-    "print(f\"Merged model: {os.path.join(OUTPUT_DIR, 'merged')}\")\n",
-    "print(\"\\n📥 Download from: Kaggle → Output tab\")"
-   ]
-  }
- ],
- "metadata": {
-  "kaggle": {
-   "accelerator": "gpu",
-   "dataSources": [],
-   "kernelSpec": {
-    "displayName": "Python 3",
-    "language": "python",
-    "name": "python3"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}


1	+ {"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# \ud83d\ude80 Stack 2.9 - Kaggle Training Notebook\n", "\n", "Free GPU training on Kaggle\n", "\n", "This notebook trains a LoRA adapter for Stack 2.9 on Qwen2.5-Coder-7B using Kaggle's free GPU.\n", "\n", "\u23f1\ufe0f Expected runtime: 2-4 hours\n", "\ud83d\udcbe VRAM needed: ~16GB (Kaggle P100 has 16GB)\n", "\n", "---\n", "\n", "Instructions:\n", "1. Enable GPU: Settings \u2192 Accelerator \u2192 GPU P100\n", "2. Run cells in order from the top\n", "3. Model auto-downloads if not present\n", "\n", "---"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 2: Clone repo\n", "import os\n", "import shutil\n", "import subprocess\n", "\n", "REPO_DIR = \"/kaggle/working/stack-2.9\"\n", "\n", "if os.path.exists(REPO_DIR):\n", " shutil.rmtree(REPO_DIR)\n", "\n", "subprocess.run([\"git\", \"clone\", \"https://github.com/my-ai-stack/stack-2.9.git\", REPO_DIR], check=True)\n", "\n", "os.chdir(REPO_DIR)\n", "print(f\"\u2705 Working in: {os.getcwd()}\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 3: Install dependencies\n", "import subprocess\n", "subprocess.run([\"pip\", \"install\", \"-q\", \"torch\", \"torchvision\", \"torchaudio\", \"--index-url\", \"https://download.pytorch.org/whl/cu118\"], check=True)\n", "subprocess.run([\"pip\", \"install\", \"-q\", \"transformers\", \"peft\", \"accelerate\", \"datasets\", \"pyyaml\", \"tqdm\", \"scipy\", \"bitsandbytes\"], check=True)\n", "print(\"\u2705 Dependencies installed\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 3: Install dependencies\n", "!pip install -q torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\n", "!pip install -q transformers peft accelerate datasets pyyaml tqdm scipy bitsandbytes\n", "print(\"\u2705 Dependencies installed\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 4: Setup paths (MODEL_DIR, OUTPUT_DIR)\n", "import os\n", "\n", "REPO_DIR = \"/kaggle/working/stack-2.9\"\n", "MODEL_DIR = os.path.join(REPO_DIR, \"base_model_qwen7b\")\n", "OUTPUT_DIR = os.path.join(REPO_DIR, \"training_output\")\n", "\n", "print(f\"REPO_DIR: {REPO_DIR}\")\n", "print(f\"MODEL_DIR: {MODEL_DIR}\")\n", "print(f\"OUTPUT_DIR: {OUTPUT_DIR}\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 5: Download model (if not exists)\n", "from transformers import AutoModelForCausalLM, AutoTokenizer\n", "\n", "if os.path.exists(os.path.join(MODEL_DIR, \"config.json\")):\n", " print(\"\u2705 Model already exists, skipping download!\")\n", "else:\n", " print(\"\u2b07\ufe0f Downloading model (Qwen2.5-Coder-7B)...\")\n", " print(\"This takes ~10-15 minutes...\")\n", " tokenizer = AutoTokenizer.from_pretrained(\"Qwen/Qwen2.5-Coder-7B\", trust_remote_code=True)\n", " tokenizer.save_pretrained(MODEL_DIR)\n", " model = AutoModelForCausalLM.from_pretrained(\"Qwen/Qwen2.5-Coder-7B\", trust_remote_code=True)\n", " model.save_pretrained(MODEL_DIR)\n", " print(\"\u2705 Model downloaded!\")\n", "\n", "import subprocess\n", "subprocess.run([\"ls\", \"-lh\", MODEL_DIR], check=True)"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 6: Create config\n", "import yaml\n", "import os\n", "\n", "os.makedirs(OUTPUT_DIR, exist_ok=True)\n", "\n", "config = {\n", " 'model': {'name': MODEL_DIR, 'trust_remote_code': True, 'torch_dtype': 'float16'},\n", " 'data': {'input_path': './data/final/train.jsonl', 'max_length': 2048},\n", " 'lora': {'r': 16, 'alpha': 32, 'dropout': 0.05,\n", " 'target_modules': ['q_proj', 'k_proj', 'v_proj', 'o_proj'],\n", " 'bias': 'none', 'task_type': 'CAUSAL_LM'},\n", " 'training': {'num_epochs': 1, 'batch_size': 2, 'gradient_accumulation': 4,\n", " 'learning_rate': 2e-4, 'warmup_steps': 50, 'weight_decay': 0.01,\n", " 'max_grad_norm': 1.0, 'logging_steps': 5, 'eval_steps': 100,\n", " 'save_steps': 200, 'save_total_limit': 2, 'fp16': True, 'bf16': False,\n", " 'gradient_checkpointing': True},\n", " 'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'),\n", " 'merged_dir': os.path.join(OUTPUT_DIR, 'merged')},\n", " 'quantization': {'enabled': False},\n", " 'hardware': {'device': 'cuda', 'num_gpus': 1, 'use_4bit': False, 'use_8bit': False}\n", "}\n", "\n", "config_path = os.path.join(OUTPUT_DIR, \"train_config.yaml\")\n", "with open(config_path, 'w') as f:\n", " yaml.dump(config, f)\n", "\n", "print(f\"\u2705 Config saved to: {config_path}\")\n", "print(f\" Device: {config['hardware']['device']}\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 7: Train LoRA\n", "import sys\n", "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n", "\n", "print(\"=\"60)\n", "print(\"STARTING TRAINING\")\n", "print(\"=\"60)\n", "\n", "from train_lora import train_lora\n", "trainer = train_lora(config_path)\n", "\n", "print(\"=\"60)\n", "print(\"TRAINING COMPLETED!\")\n", "print(\"=\"60)"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 8: Merge model\n", "import sys\n", "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n", "from merge_adapter import merge_adapter\n", "\n", "merged_dir = os.path.join(OUTPUT_DIR, \"merged\")\n", "os.makedirs(merged_dir, exist_ok=True)\n", "\n", "merge_config = {\n", " 'model': {'name': MODEL_DIR, 'trust_remote_code': True},\n", " 'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'), 'merged_dir': merged_dir},\n", " 'quantization': {'enabled': False}\n", "}\n", "\n", "merge_cfg_path = os.path.join(OUTPUT_DIR, \"merge_config.yaml\")\n", "with open(merge_cfg_path, 'w') as f:\n", " yaml.dump(merge_config, f)\n", "\n", "merge_adapter(merge_cfg_path, os.path.join(OUTPUT_DIR, \"lora\"), merged_dir)\n", "\n", "print(f\"\u2705 Merged model saved to: {merged_dir}\")\n", "import subprocess\n", "subprocess.run([\"ls\", \"-lh\", merged_dir], check=True)"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 9: Done!\n", "print(\"=\"60)\n", "print(\"\ud83c\udf89 TRAINING COMPLETE!\")\n", "print(\"=\"60)\n", "print(f\"LoRA adapter: {os.path.join(OUTPUT_DIR, 'lora')}\")\n", "print(f\"Merged model: {os.path.join(OUTPUT_DIR, 'merged')}\")\n", "print(\"\\n\ud83d\udce5 Download from: Kaggle \u2192 Output tab\")"]}], "metadata": {"kaggle": {"accelerator": "gpu", "dataSources": [], "kernelSpec": {"displayName": "Python 3", "language": "python", "name": "python3"}}}, "nbformat": 4, "nbformat_minor": 0}