Ian O'Brien 👨‍🚀 @TechnicallyIan

Greenwich, CT Joined January 2013

Tweets

482
Followers

317
Following

105
Likes

2K

Baseten @basetenco

a year ago

We’ve updated our evaluation of the best open source LLMs and—spoiler alert—Llama 3 70B Instruct tops the list. Our complete recommendations: baseten.co/blog/the-best-…

1 4 68 5K 3

We’re excited to launch Meta’s Llama 3 in our model library, in both 8B and 70B 🎉 The newly introduced Llama 3 is a significant improvement over Llama 2, with increased tokens, and reduced false refusal rates. These models deliver unparalleled performance, showcasing…

7 22 237 131K 9

Baseten @basetenco

a year ago

Deploy Mixtral 8x22B in one click! Mixtral fast facts: - #1 pretrained model on the Open LLM leaderboard - Mixture of Experts architecture - Apache 2.0 license - Uses 4 A100s in fp16, optimized implementations coming soon! baseten.co/library/mixtra…

2 7 28 5K 3

Baseten @basetenco

a year ago

Another first 🎉 Unlock the power of @nvidia's Multi-Instance GPU (MIG) virtualization technology with H100mig GPUs on Baseten: baseten.co/changelog/frac…

3 7 21 8K 3

Baseten @basetenco

2 years ago

40% lower latency and 70% higher throughput for Stable Diffusion XL? Using NVIDIA TensorRT to optimize each component of the SDXL image generation pipeline, we achieved these performance gains on an H100 GPU. Full results: baseten.co/blog/40-faster…

2 11 29 8K 7

Baseten @basetenco

2 years ago

Nomic Embed v1.5 outperforms OpenAI's text-embedding-3-small and ada-002, plus offers variable dimensionality. This best in class open source text embedding model from @nomic_ai is now available for 1-click deployment in Baseten's model library: baseten.co/library/nomic-…

1 4 11 2K 1

Baseten @basetenco

2 years ago

Unlocking the full potential of GPUs requires optimizing every part of the model serving stack. Using TensorRT from @nvidia, we optimize ML models to take full advantage of the H100 Hopper architecture, providing 20-40% better performance per dollar. baseten.co/blog/unlocking…

1 5 9 839 0

Baseten @basetenco

2 years ago

Launching today 🎉 Double your throughput or halve your latency for @MistralAI, @StabilityAI + others? Do both at ~20% lower cost with @nvidia H100s on Baseten. Here’s how 👇

2 16 39 10K 15

Baseten @basetenco

2 years ago

Mixtral 8x7B beats Llama 2 70B on quality for many benchmarks, but it also wins on inference speed. Here’s why: - Mixtral is only 46.7B parameters - Only 12.9B are used during inference - You can make it even faster with TensorRT-LLM and int8 quantization

1 5 15 1K 2

Download Image

Baseten @basetenco

2 years ago

Stable Video Diffusion is so much fun. You can now deploy it yourself on Baseten. @StabilityAI knocked it out of the park with this one 🎉 Lots of examples in the thread below 🧵 baseten.co/blog/stable-vi…

1 6 13 2K 1

Baseten @basetenco

2 years ago

Ready to try open source LLMs? Switch from GPT to Mistral 7B in the smallest refactor you'll ever ship: just 3 tiny code changes. If you're making the jump, DM us for $1,000 in free credits. baseten.co/blog/gpt-vs-mi…

0 8 15 2K 1

Philip Kiely @philip_kiely

2 years ago

I’ll be at AWS re:Invent at the end of the month. Stop by the Baseten booth in the expo hall and say hi!

0 1 5 572 0

Download Image

Practical AI 🤖 @PracticalAIFM

2 years ago

🔥 New episode of Practical AI! 🗣 Self-hosting & scaling models ✨ featuring @tuhinone from @basetenco ⚡️ hosts @chrisbenson & @dwhitena 🗄️ #ai #machinelearning #mlops 💚 practicalai.fm/243

0 2 2 512 1

Baseten @basetenco

2 years ago

There's a new text embedding model by @JinaAI_ with some exciting properties 👀 - 8,192-token context window (embed chapters, not pages) - Matches OpenAI's ada-002 on popular benchmarks Use jina-embeddings-v2 for search & recommendations and pair w/ LLMs like Mistral for RAG.

2 1 7 836 0

Julien from Baseten @JulienTech

2 years ago

Huge thank you to the ML creators who attended @basetenco's #TechWeek events! Learned a ton from our panel of leaders at @tryramp, @NormalComputing, @PatronusAI, and @GoldmanSachs. Our ML party was a huge hit, with devs from @Meta, @stripe, and @Google. Can't wait for more!

0 2 21 3K 0

Download Image

Baseten @basetenco

2 years ago

Presenting your winner, by unanimous decision… ANDDD… NEW seven billion parameter champion of the world... Mistral 7B blew past Llama 2 on the benchmarks. And it can code, too. Get Mistral 7B with streaming output behind an API endpoint in minutes: app.baseten.co/explore/mistra…

0 3 11 7K 6

Alex MacCaw @maccaw

2 years ago

For serverless models, I'm super impressed by baseten.co's team. They fixed one example model, and then added another model I requested, all in ten minutes. And easily the fastest server response times too.

2 11 58 21K 28

naklecha @naklecha

2 years ago

@JulienTech @basetenco I haven't seen a GPU start and load my model faster than @basetenco. It goes from 0 to fully operational in a few seconds. You guys are killing it!

0 3 13 1K 0

Varun Shenoy @varunshenoy_

2 years ago

Introducing Opendream, a better interface for diffusion models 👨‍🎨 Opendream brings much needed features to your workflow, such as: - writing extensions as single Python functions 👀 - layering and non-destructive editing 🍰 - saving and sharing 💾 And it's all open-source.

6 36 267 36K 100

Download Video

Baseten @basetenco

2 years ago

We’ve got drinks, dinner, demos, and discussion - all we need is you! Join builders and founders at our next AI meetup this Thursday, August 10th, in San Francisco.