Today we're launching BaseTen. We've been working hard over the last 18 months to build the tool that we wished we had to operationalize our models.
Please check it out, and if you're interested, we'd love to give you early access!
🎉 We’re really excited to be announcing BaseTen today.
BaseTen is the fastest way to build applications powered by machine learning.
Check it out yourself!
baseten.co/blog
And we're live! We're excited to announce the public beta of @baseten to allow you to build full-stack applications around your machine learning models.
We raised a $40M Series B to power the next generation of AI products with best-in-class infrastructure.
In the last year, companies like @descript@gammaapp@PicnicHealth, @Writer, @Patreon and @usebland have scaled inference on Baseten — all with zero minutes of downtime.
We keep getting asked by users if they can use the 70B parameter model in production.
We're serving the chat variant of Llama-2 70B on 2xA100 and getting pretty great throughput — it's cooking!
👋 Meet Blueprint: An easy way for developers to fine-tune and serve open source foundation models.
Check it out here: blueprint.baseten.co
🧵 A thread on why we built Blueprint and what you can do with it:
We're very excited to be an @OpenAI launch partner for GPT OSS. Today's a big day for open models, and we have day 0 support for GPT OSS 120b via our Model APIs: baseten.co/library/gpt-os…
We'll be rolling out more performance optimizations and benchmarks over the coming hours and
Bark's awesome — it's also clear that the maintainers care about people being able to use their model. It's one of the first repos I've seen where the code/examples *just work*, and the tiny hardware section of this repo should be the norm.
github.com/suno-ai/bark
I couldn't be happier to announce that Dannie is joining Baseten as President, leading GTM and operations. Baseten is growing incredibly fast, fueled by the growth of our amazing customers. I can think of no better person to help usher us into the next chapter of our company's
Welcome to Baseten @DannieHerz!
We’re thrilled to announce that Dannie Herzberg has joined as our new President to lead Baseten’s GTM and operations.
As @tuhinone shared: "Dannie is biased towards action, dependable, and long-term in her thinking, and she knows that the
:) @aaronrelph, @aqaderb, @suren_at instruction tuned llama on the alpaca dataset, open-sourced the model with @huggingface, served it with @baseten, and built a chatbot on top of it in a couple of days.
hacker energy in ML is 💪🏾
It's been a wild couple of years. Thanks to all our customers who partnered with us as they bring their AI products to market. It feels like we're at the precipice of something bigger.
We've raised some more capital. This isn't the important part of the company or the journey.
Baseten launches Mistral 7B API with leading performance 🚀
@baseten has entered the arena with their first serverless LLM offering of Mistral 7B Instruct. Artificial Analysis are measuring 170 tokens per second, the fastest of any provider, and 0.1s latency (TTFT) in-line
