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", device_map="auto")
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
```

walidsobhie-code commited on Apr 5

Commit

98e3329

1 Parent(s): c2013aa

fix: set expandable_segments=False to fix PyTorch #124807 gradient checkpointing bug

Browse files

Files changed (1) hide show

train_simple_nobnb.py +3 -2

train_simple_nobnb.py CHANGED Viewed

@@ -144,7 +144,8 @@ def train(config: dict):
     use_8bit = hardware_config.get("use_8bit", False)
     # Set environment variables for better CUDA memory management
-    os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True,max_split_size_mb:512"
     # Clear CUDA cache before loading
     if torch.cuda.is_available():
@@ -229,7 +230,7 @@ def train(config: dict):
         report_to="none",
         dataloader_num_workers=0,
         remove_unused_columns=False,
-        optim="paged_adamw_32bit" if (use_4bit or use_8bit) else "adamw_torch",
     )
     data_collator = DataCollatorForLanguageModeling(

     use_8bit = hardware_config.get("use_8bit", False)
     # Set environment variables for better CUDA memory management
+    # expandable_segments:False fixes a known PyTorch bug (#124807, #128829) with gradient checkpointing
+    os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:False"
     # Clear CUDA cache before loading
     if torch.cuda.is_available():
         report_to="none",
         dataloader_num_workers=0,
         remove_unused_columns=False,
+        optim="paged_adamw_32bit" if (use_4bit or use_8bit) else "adamw_torch_fused",
     )
     data_collator = DataCollatorForLanguageModeling(