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
```

Stack-2-9-finetuned / stack /training /train_config_colab.yaml

walidsobhie-code

refactor: Squeeze folders further - cleaner structure

65888d5 about 2 months ago

raw

history blame contribute delete

2.47 kB

	# Colab-Optimized Training Configuration for Stack 2.9
	# Target: Google Colab free tier (T4 GPU, 15GB VRAM)
	# Model: Qwen/Qwen2.5-Coder-7B (4-bit quantized fits in ~4.5GB)
	# Expected runtime: 3-5 hours

	model:
	name: "Qwen/Qwen2.5-Coder-7B" # 7B instead of 32B for Colab
	trust_remote_code: true
	use_flash_attention: false # T4 doesn't support flash attention well

	tokenizer:
	model_max_length: 8192 # Reduced from 131072 for memory
	padding_side: "right"
	truncation_side: "right"

	peft:
	peft_type: "LORA"
	task_type: "CAUSAL_LM"
	r: 16 # LoRA rank (lower = faster, good enough for 7B)
	lora_alpha: 32
	lora_dropout: 0.05
	target_modules:
	- "q_proj"
	- "k_proj"
	- "v_proj"
	- "o_proj"
	- "gate_proj"
	- "up_proj"
	- "down_proj"
	# Optional: add "embed_tokens", "lm_head" for full coverage (increases memory)

	quantization:
	load_in_4bit: true
	bnb_4bit_compute_dtype: "bfloat16"
	bnb_4bit_quant_type: "nf4"
	bnb_4bit_use_double_quant: true

	training:
	output_dir: "./adapters_colab"
	num_train_epochs: 2 # Sufficient for 7B with decent dataset
	per_device_train_batch_size: 1 # Tiny batch for 15GB VRAM
	gradient_accumulation_steps: 16 # Effective batch size = 16
	optim: "paged_adamw_8bit" # 8-bit optimizer for memory
	learning_rate: 1.0e-4
	weight_decay: 0.01
	warmup_steps: 100
	lr_scheduler_type: "cosine"
	save_steps: 500
	save_total_limit: 2
	logging_steps: 10
	report_to: "none" # Disable wandb for Colab

	# Memory optimizations
	gradient_checkpointing: true
	fp16: false # Use bf16 instead if available
	bf16: true # T4 supports bf16
	max_grad_norm: 1.0
	dataloader_num_workers: 2
	remove_unused_columns: false

	data:
	train_file: "./training-data/train.jsonl"
	validation_file: "./training-data/eval.jsonl"
	dataset_format: "chat" # or "prompt_response"
	max_seq_length: 8192 # Critical for T4 memory
	prompt_template: "chatml" # Qwen's default template

	# Hardware
	ddp: false # Single GPU for Colab

	# Misc
	seed: 42
	push_to_hub: false # Set to true and add HF token to push during training
	hub_model_id: null # "your-org/stack-2.9-7b-lora"

	# Notes:
	# - 4-bit quantization + batch size 1 + gradient checkpointing = fits in 15GB
	# - If OOM: reduce max_seq_length to 4096 or increase gradient_accumulation_steps
	# - If training is slow: increase per_device_train_batch_size to 2 (if memory allows)
	# - After training, merge adapter with base model using merge_adapter.py