Hugging Face logoHugging Face

Hugging Face, via their H4 research team, fine tunes LLMs like Mistral for alignment and scores them on evaluation benchmarks.

Hugging Face models

Hugging Face logoZephyr 7B Alpha

LLM
AlphaA10G

About Hugging Face

Hugging Face is a platform for ML model repositories and creates toolkits for ML development like the transformers library. Hugging Face was founded in 2016 and is headquartered in New York City. 

Hugging Face H4 is a research team focused on aligning language models to be “helpful, honest, harmless, and huggy.” The team fine tunes foundation models like Mistral 7B on a mix of public and synthetic datasets to turn base models into helpful assistants that score well on evaluation benchmarks.

Deploy any model in just a few commands

Avoid getting tangled in complex deployment processes. Deploy best-in-class open-source models and take advantage of optimized serving for your own models.

$

truss init -- example stable-diffusion-2-1-base ./my-sd-truss

$

cd ./my-sd-truss

$

export BASETEN_API_KEY=MdNmOCXc.YBtEZD0WFOYKso2A6NEQkRqTe

$

truss push

INFO

Serializing Stable Diffusion 2.1 truss.

INFO

Making contact with Baseten 👋 👽

INFO

🚀 Uploading model to Baseten 🚀

Upload progress: 0% | | 0.00G/2.39G