Skunkworks AI @skunkworks_ai Twitter profile

Last Seen Profiles

@RealTPlatform

@CheLaPlu

@SentaKarin99997

@wotantyshirt

@snailyslop

@_TFrancis444

@RAINN

@_somaz_

@Watcher096

@vermaabhishek25

@savcds

@Caluben_

@datesofarton

@YaroslavConway

@jaestheticc_

@PazSensei96

@ValTsports

@TheOtakuPatriot

@GVsftball

@AMDServer

@DrivePlanoSeque

@i95jnghan_

@Jatavionsanders

@ErikDoesStuff04

@Forward_2020

@touyaseyelashes

@MarisaL_Aragon

@AaronMorales_7

@GPEC

@stw_pdg

@CrystalFissure

@cornistyan

@JarasJarasy

@BillyyMcCann

@krisiannc

@AgonysAIO

Skunkworks AI

@skunkworks_ai

7 months

BakLLaVA 1 can successfully see! And we're not even half way through our run 👀 The base model is a Mistral 7B, so this is possibly the first @MistralAI vision model! Model is hosted here and will be fully released soon:

25

106

669

Skunkworks AI

@skunkworks_ai

7 months

BakLLaVA-1 is now available to everyone. We show Mistral-7B with vision outperforms Llama-2 13B on several tasks, but we've only scratched the surface. BakLLaVA-2 is cooking with a larger corpus and significant architectural improvements/innovations.

SkunkworksAI/BakLLaVA-1 · Hugging Face

huggingface.co

18

83

456

Skunkworks AI

@skunkworks_ai

7 months

Releasing Mistralic-7B-1, the first of many Mistral finetunes which pushes Mistral further into SOTA territory while improving coding capabilities.

SkunkworksAI/Mistralic-7B-1 · Hugging Face

huggingface.co

7

15

211

Skunkworks AI

@skunkworks_ai

8 months

We are now ready to scale MoE with the objective of achieving GPT-4 performance thanks to our core team member @Sentdex and for @togethercompute for elevating us from GPU Poor to GPU Middle Class. Join our group and contribute to help accelerate OSS AI!

1

6

71

Skunkworks AI

@skunkworks_ai

7 months

This model was forged thanks to the generous support from @togethercompute . We'll continue to push the multimodal model further in collaboration with @ontocord @cliangyu_ @laion_ai @alignment_lab with an even more powerful v2 coming soon.

0

2

47

Skunkworks AI

@skunkworks_ai

7 months

We're getting hundreds of access requests every day since we announced BakLLaVA v1 🚀 We'll open the flood gates shortly. Stay tuned.

2

5

41

Skunkworks AI

@skunkworks_ai

7 months

We baking BakLLaVA to push vision LLMs even further! New vision models incoming. @sentdex @ontocord @nisten @far__el Thank you @togethercompute for supporting this OSS initiative!

2

1

32

Skunkworks AI

@skunkworks_ai

7 months

As always, thank you to our compute sponsor @togethercompute and to our collaborators @ontocord @Sentdex @laion_ai @alignment_lab . We can't wait to show you what we're up to with the next updates! Demo for BakLLaVA-1 coming soon. ( @ClementDelangue @huggingface 👀)

2

6

22

Skunkworks AI

@skunkworks_ai

8 months

It's time to forge open AI. @togethercompute

1

2

16

Skunkworks AI

@skunkworks_ai

7 months

Try it out on this colab notebook!

Mistralic-1-7B.ipynb

Colaboratory notebook

colab.research.google.com

0

13

Skunkworks AI

@skunkworks_ai

7 months

@togethercompute @ontocord @Sentdex @laion_ai @alignment_lab @ClementDelangue @huggingface Please do check out the OG LLaVA implementation by @imhaotian ! Here:

0

12

Skunkworks AI

@skunkworks_ai

1 year

@ylecun @kchonyc We need a more rational, balanced and optimistic narrative

4

0

8

Skunkworks AI

@skunkworks_ai

7 months

Special thanks to Together Compute for sponsoring Skunkworks with compute! @togethercompute This is just the beginning of many releases coming in the next weeks pushing the boundaries of OSS AI even further. Stay tuned for MoE updates!

1

0

7

Skunkworks AI

@skunkworks_ai

7 months

@AdarrabYoussef BakLLaVA-1's code is a fork of adapted for Mistral-7B. Here's our repo (although some updates coming over the next day to clean up and incorporate some new features we added)