Instructions to use 080-ai/tiny-cutlass with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 080-ai/tiny-cutlass with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="080-ai/tiny-cutlass")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("080-ai/tiny-cutlass")
model = AutoModelForCausalLM.from_pretrained("080-ai/tiny-cutlass")
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]:]))

PEFT
How to use 080-ai/tiny-cutlass with PEFT:
```
Task type is invalid.
```
Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 080-ai/tiny-cutlass with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "080-ai/tiny-cutlass"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "080-ai/tiny-cutlass",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/080-ai/tiny-cutlass

SGLang

How to use 080-ai/tiny-cutlass 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 "080-ai/tiny-cutlass" \
    --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": "080-ai/tiny-cutlass",
		"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 "080-ai/tiny-cutlass" \
        --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": "080-ai/tiny-cutlass",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 080-ai/tiny-cutlass with Docker Model Runner:
```
docker model run hf.co/080-ai/tiny-cutlass
```

ambrosfitz commited on May 3, 2024

Commit

ab6fc96

verified ·

1 Parent(s): bd5942b

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

runs/May03_19-39-04_bf437c1c2037/events.out.tfevents.1714765168.bf437c1c2037.12072.0 +3 -0
runs/May03_20-14-55_bf437c1c2037/events.out.tfevents.1714767299.bf437c1c2037.21192.0 +3 -0

runs/May03_19-39-04_bf437c1c2037/events.out.tfevents.1714765168.bf437c1c2037.12072.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d39d3415d1ee0cd68c484a476da74c708f28c3e96224bcb38eb16c0cb92d942d
+size 9155

runs/May03_20-14-55_bf437c1c2037/events.out.tfevents.1714767299.bf437c1c2037.21192.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e381235bebe31d20ad42fcf1d0ec48754eca9390e48346b2f31d77d3da659faf
+size 4184