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 3

Commit

2c32ffd

1 Parent(s): e31f34c

fix: syntax errors in notebook and create_mini_dataset script

Browse files

- Fix missing print() in training cell
- Fix missing print() in merge cell
- Add missing typing imports (List, Dict) in create_mini_dataset.py

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

Files changed (2) hide show

colab_train_stack29.ipynb +2 -58
scripts/create_mini_dataset.py +1 -0

colab_train_stack29.ipynb CHANGED Viewed

@@ -241,30 +241,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import os\n",
-    "import sys\n",
-    "\n",
-    "# Add training module to path\n",
-    "sys.path.insert(0, './stack/training')\n",
-    "\n",
-    "print(\"=\"*60)\n",
-    "print(\"STARTING TRAINING\")\n",
-    "=\"*60)\n",
-    "print(f\"Working directory: {os.getcwd()}\")\n",
-    "print(f\"Config: {updated_config_path}\")\n",
-    "print(f\"Output: {OUTPUT_DIR}/lora\")\n",
-    "print(\"=\"*60 + \"\\n\")\n",
-    "\n",
-    "# Run training\n",
-    "from train_lora import train_lora\n",
-    "\n",
-    "trainer = train_lora(updated_config_path)\n",
-    "\n",
-    "print(\"\\n\" + \"=\"*60)\n",
-    "print(\"TRAINING FINISHED OR STOPPED\")\n",
-    "print(\"=\"*60)"
-   ]
   },
   {
    "cell_type": "markdown",
@@ -306,40 +283,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import yaml\n",
-    "import sys\n",
-    "\n",
-    "sys.path.insert(0, './stack/training')\n",
-    "from merge_adapter import merge_adapter\n",
-    "\n",
-    "merged_dir = f\"{OUTPUT_DIR}/merged\"\n",
-    "\n",
-    "print(\"=\"*60)\n",
-    "print(\"MERGING LORA ADAPTER\")\n",
-    "=\"*60)\n",
-    "\n",
-    "# Create merge config\n",
-    "merge_config = {\n",
-    "    'model': {'name': MODEL_DIR, 'trust_remote_code': True},\n",
-    "    'output': {'lora_dir': f'{OUTPUT_DIR}/lora', 'merged_dir': merged_dir},\n",
-    "    'quantization': {'enabled': False}\n",
-    "}\n",
-    "\n",
-    "merge_config_path = f\"{OUTPUT_DIR}/merge_config.yaml\"\n",
-    "with open(merge_config_path, 'w') as f:\n",
-    "    yaml.dump(merge_config, f)\n",
-    "\n",
-    "# Run merge\n",
-    "merge_adapter(\n",
-    "    config_path=merge_config_path,\n",
-    "    lora_path=f\"{OUTPUT_DIR}/lora\",\n",
-    "    output_path=merged_dir\n",
-    ")\n",
-    "\n",
-    "print(f\"\\n✅ Merged model saved to: {merged_dir}\")\n",
-    "!ls -lh {merged_dir}/"
-   ]
   },
   {
    "cell_type": "markdown",

    "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": "import os\nimport sys\n\n# Add training module to path\nsys.path.insert(0, './stack/training')\n\nprint(\"=\"*60)\nprint(\"STARTING TRAINING\")\nprint(\"=\"*60)\nprint(f\"Working directory: {os.getcwd()}\")\nprint(f\"Config: {updated_config_path}\")\nprint(f\"Output: {OUTPUT_DIR}/lora\")\nprint(\"=\"*60 + \"\\n\")\n\n# Run training\nfrom train_lora import train_lora\n\ntrainer = train_lora(updated_config_path)\n\nprint(\"\\n\" + \"=\"*60)\nprint(\"TRAINING FINISHED OR STOPPED\")\nprint(\"=\"*60)"
   },
   {
    "cell_type": "markdown",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": "import yaml\nimport sys\n\nsys.path.insert(0, './stack/training')\nfrom merge_adapter import merge_adapter\n\nmerged_dir = f\"{OUTPUT_DIR}/merged\"\n\nprint(\"=\"*60)\nprint(\"MERGING LORA ADAPTER\")\nprint(\"=\"*60)\n\n# Create merge config\nmerge_config = {\n    'model': {'name': MODEL_DIR, 'trust_remote_code': True},\n    'output': {'lora_dir': f'{OUTPUT_DIR}/lora', 'merged_dir': merged_dir},\n    'quantization': {'enabled': False}\n}\n\nmerge_config_path = f\"{OUTPUT_DIR}/merge_config.yaml\"\nwith open(merge_config_path, 'w') as f:\n    yaml.dump(merge_config, f)\n\n# Run merge\nmerge_adapter(\n    config_path=merge_config_path,\n    lora_path=f\"{OUTPUT_DIR}/lora\",\n    output_path=merged_dir\n)\n\nprint(f\"\\n✅ Merged model saved to: {merged_dir}\")\n!ls -lh {merged_dir}/"
   },
   {
    "cell_type": "markdown",

scripts/create_mini_dataset.py CHANGED Viewed

@@ -8,6 +8,7 @@ import argparse
 import json
 import random
 from pathlib import Path
 from collections import defaultdict, Counter
 def load_full_dataset(train_path: str = "training-data/final/train.jsonl") -> List[Dict]:

 import json
 import random
 from pathlib import Path
+from typing import List, Dict
 from collections import defaultdict, Counter
 def load_full_dataset(train_path: str = "training-data/final/train.jsonl") -> List[Dict]: