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

f268fb6

1 Parent(s): 1c64613

docs: update README with training options and RTMP extraction

Browse files

- Add training options table (Colab, Kaggle, Local Mac, Cloud)
- Add RTMP tool extraction instructions
- Add Kaggle notebook reference

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

Files changed (1) hide show

README.md +57 -0

README.md CHANGED Viewed

@@ -245,6 +245,15 @@ python scripts/merge_lora_adapters.py \
 ## 🛠️ Training & Fine-Tuning
 ### Quick Training (Colab)
 Use the provided notebook for quick prototyping:
@@ -281,6 +290,54 @@ For production training on GPUs:
 See each script for usage instructions.
 ---
 ## 🐳 Deployment

 ## 🛠️ Training & Fine-Tuning
+### Training Options
+| Platform | Notebook | Description |
+|----------|----------|-------------|
+| **Google Colab** | `colab_train_stack29.ipynb` | Free T4 GPU, 3-5 hours |
+| **Kaggle** | `kaggle_train_stack29.ipynb` | Free P100 GPU, 2-4 hours |
+| **Local Mac** | `train_local.py` | MPS/Apple Silicon |
+| **Cloud GPUs** | See below | RunPod, Vast.ai, etc |
 ### Quick Training (Colab)
 Use the provided notebook for quick prototyping:
 See each script for usage instructions.
+### Extracting Training Data from Your Codebase
+Extract tool patterns from your codebase to train the model:
+```bash
+# Extract tool patterns
+python scripts/extract_rtmp_tools.py
+# Create advanced examples
+python scripts/extract_rtmp_tools_advanced.py
+```
+This creates `data/rtmp-tools/` with tool usage patterns that can be combined with the main training data.
+### Kaggle Training
+Free GPU training on Kaggle (P100 16GB VRAM):
+```bash
+# Open in Kaggle
+kaggle_train_stack29.ipynb
+```
+### Local Mac Training (MPS)
+For Apple Silicon Macs without GPU cloud access:
+```bash
+python train_local.py
+```
+### Extracting Tool Patterns from RTMP
+Extract training data from your RTMP codebase to teach the model your custom tools:
+```bash
+# Extract tool patterns
+python scripts/extract_rtmp_tools.py
+python scripts/extract_rtmp_tools_advanced.py
+# Combined data includes 46+ tool patterns
+data/rtmp-tools/combined_tools.jsonl
+```
+The combined training data includes:
+- 41,807 code completion examples
+- 59 RTMP tool usage patterns (BashTool, FileReadTool, Task tools, etc.)
 ---
 ## 🐳 Deployment