Instructions to use open-machine/Llama-3.1-8B-FlashNorm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-machine/Llama-3.1-8B-FlashNorm with Transformers:

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

pipe = pipeline("text-generation", model="open-machine/Llama-3.1-8B-FlashNorm")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-machine/Llama-3.1-8B-FlashNorm")
model = AutoModelForCausalLM.from_pretrained("open-machine/Llama-3.1-8B-FlashNorm")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use open-machine/Llama-3.1-8B-FlashNorm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-machine/Llama-3.1-8B-FlashNorm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "open-machine/Llama-3.1-8B-FlashNorm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/open-machine/Llama-3.1-8B-FlashNorm

SGLang

How to use open-machine/Llama-3.1-8B-FlashNorm 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 "open-machine/Llama-3.1-8B-FlashNorm" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "open-machine/Llama-3.1-8B-FlashNorm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "open-machine/Llama-3.1-8B-FlashNorm" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "open-machine/Llama-3.1-8B-FlashNorm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use open-machine/Llama-3.1-8B-FlashNorm with Docker Model Runner:
```
docker model run hf.co/open-machine/Llama-3.1-8B-FlashNorm
```

Add library_name metadata and link to paper

by nielsr HF Staff - opened Apr 23

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+24

-7

nielsr

Apr 23

Hi! I'm Niels from the Hugging Face team. This PR adds the library_name: transformers metadata to the model card, enabling the "Use in Transformers" button on the Hub. I've also ensured the model card clearly links to the paper presenting FlashNorm and added the BibTeX citation.

Add library_name metadata and link to paper6217a471

graefics

OpenMachine org Apr 23

Awesome, thank you! I appreciate you doing this!

graefics changed pull request status to merged Apr 23

graefics

OpenMachine org Apr 23

On second thought: could you update the paper title and authors to the latest, as follows?
'FlashNorm: Fast Normalization for Transformers' by Nils Graef, Filip Makraduli, Andrew Wasielewski, Matthew Clapp

If possible, could you also please update the HF paper page https://huggingface.co/papers/2407.09577 with the new title and latest author list?

Thank you!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment