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 Settings

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
```

Stack-2-9-finetuned / colab_train_stack29.ipynb

Commit History

fix: skip model download to avoid crashes

fd566cb

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: skip model download if it exists, avoid crashes

a6de582

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: add retry logic for git clone

57be99c

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: define all paths in first cell for kernel restart safety

f90ca5c

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: add imports to each cell for robustness

9008611

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: create sample data if real data not found in repo

468b3cf

walidsobhie-code commited on Apr 4

refactor: simplify notebook with single ROOT_DIR variable

de15016

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: use different base path to avoid nested directory issue

389f026

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: force fresh clone to get latest script fixes

a9f935e

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: handle nested directory and data path issues

2f44834

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: add nested directory detection and auto-fix

8c5fec7

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: add error checking and absolute paths for config and data

235cb20

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: use absolute paths and fix bitsandbytes version

c98eba8

walidsobhie-code Claude Opus 4.6 commited on Apr 4

fix: syntax errors in notebook and create_mini_dataset script

2c32ffd

walidsobhie-code Claude Opus 4.6 commited on Apr 3

fix: update notebook for Colab T4 GPU training

e31f34c

walidsobhie-code Claude Opus 4.6 commited on Apr 3

Fix colab training notebook for local Mac MPS training

e5ae26c

walidsobhie-code Claude Opus 4.6 commited on Apr 3

feat: add TypeScript modules and reorganize project structure

bfc7d04

walidsobhie-code Claude Opus 4.6 commited on Apr 3

feat: zero-cost Colab training pipeline and proper evaluation

49ffe54

walidsobhie-code commited on Apr 2

Commit History

fix: skip model download to avoid crashes fd566cb

fix: skip model download if it exists, avoid crashes a6de582

fix: add retry logic for git clone 57be99c

fix: define all paths in first cell for kernel restart safety f90ca5c

fix: add imports to each cell for robustness 9008611

fix: create sample data if real data not found in repo 468b3cf

refactor: simplify notebook with single ROOT_DIR variable de15016

fix: use different base path to avoid nested directory issue 389f026

fix: force fresh clone to get latest script fixes a9f935e

fix: handle nested directory and data path issues 2f44834

fix: add nested directory detection and auto-fix 8c5fec7

fix: add error checking and absolute paths for config and data 235cb20

fix: use absolute paths and fix bitsandbytes version c98eba8

fix: syntax errors in notebook and create_mini_dataset script 2c32ffd

fix: update notebook for Colab T4 GPU training e31f34c

Fix colab training notebook for local Mac MPS training e5ae26c

feat: add TypeScript modules and reorganize project structure bfc7d04

feat: zero-cost Colab training pipeline and proper evaluation 49ffe54

fix: skip model download to avoid crashes

fd566cb

fix: skip model download if it exists, avoid crashes

a6de582

fix: add retry logic for git clone

57be99c

fix: define all paths in first cell for kernel restart safety

f90ca5c

fix: add imports to each cell for robustness

9008611

fix: create sample data if real data not found in repo

468b3cf

refactor: simplify notebook with single ROOT_DIR variable

de15016

fix: use different base path to avoid nested directory issue

389f026

fix: force fresh clone to get latest script fixes

a9f935e

fix: handle nested directory and data path issues

2f44834

fix: add nested directory detection and auto-fix

8c5fec7

fix: add error checking and absolute paths for config and data

235cb20

fix: use absolute paths and fix bitsandbytes version

c98eba8

fix: syntax errors in notebook and create_mini_dataset script

2c32ffd

fix: update notebook for Colab T4 GPU training

e31f34c

Fix colab training notebook for local Mac MPS training

e5ae26c

feat: add TypeScript modules and reorganize project structure

bfc7d04

feat: zero-cost Colab training pipeline and proper evaluation

49ffe54