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 /deploy /runpod-template.json

walidsobhie-code

refactor: Squeeze folders further - cleaner structure

65888d5 about 2 months ago

raw

history blame

2.31 kB

	{
	"name": "stack-2.9-inference",
	"description": "Stack 2.9 LLM Inference Server powered by vLLM with AWQ quantization",
	"author": "Stack Team",
	"version": "2.9.0",
	"docker_image": "your-registry/stack-2.9:latest",
	"env": [
	{
	"name": "MODEL_ID",
	"description": "Hugging Face model ID for loading",
	"default": "TheBloke/Llama-2-7B-Chat-AWQ",
	"required": true
	},
	{
	"name": "HUGGING_FACE_TOKEN",
	"description": "Hugging Face access token for gated models",
	"default": "",
	"required": false,
	"sensitive": true
	},
	{
	"name": "QUANTIZATION",
	"description": "Quantization method (awq, gptq, squeezellm, or none)",
	"default": "awq",
	"required": false
	},
	{
	"name": "TENSOR_PARALLEL_SIZE",
	"description": "Number of GPUs for tensor parallelism",
	"default": "1",
	"required": false
	},
	{
	"name": "GPU_MEMORY_UTILIZATION",
	"description": "Fraction of GPU memory to use (0.0-1.0)",
	"default": "0.9",
	"required": false
	},
	{
	"name": "MAX_MODEL_LEN",
	"description": "Maximum sequence length",
	"default": "4096",
	"required": false
	},
	{
	"name": "MAX_NUM_SEQS",
	"description": "Maximum number of sequences per batch",
	"default": "64",
	"required": false
	},
	{
	"name": "PORT",
	"description": "Port for the inference server",
	"default": "8000",
	"required": false
	}
	],
	"container_args": [
	"python3",
	"app.py"
	],
	"compute": {
	"gpu_count": 1,
	"gpu_type_id": "NVIDIA-A100-40GB-PCIe",
	"min_vcpu_count": 4,
	"min_ram_in_gb": 16,
	"max_vcpu_count": 8,
	"max_ram_in_gb": 32
	},
	"volume": {
	"size_in_gb": 50,
	"mount_path": "/home/vllm/.cache/huggingface"
	},
	"ports": [
	{
	"host_port": 8000,
	"container_port": 8000,
	"protocol": "tcp"
	}
	],
	"health_check": {
	"type": "HTTP",
	"endpoint": "/health",
	"interval": 30,
	"timeout": 10,
	"max_retries": 3
	},
	"auto_sleep": true,
	"auto_sleep_after_minutes": 30,
	"min_active_container_count": 0,
	"min_cost_usd_per_hour": 0.0,
	"max_cost_usd_per_hour": 5.0,
	"max_bid_usd_per_hour": 2.5,
	"spot": true,
	"label": "stack-2.9"
	}