Top Tweets for #LLava
If you’re a legal professional tired of struggling with manual research, and document drafti I’d love to have you on this journey.
Follow @llavaApp for the build updates. 🚀
#LegalTech #BuildInPublic #AI #NigeriaTech #Llava
3rd day, working on symbiote. Doesn't like BakLLaVA or Moondream vision model, Need to switch back to Llava and figure our way to execute more context. If you know any good free source AI vision model that works good. DM me.
#AITesting #VisionAI #OpenSourceAI #LLaVA #BakLLaVA #Moondream #ComputerVision #MachineLearning #AI #BuildInPublic #IndieDev #WebDev #TypeScript #TestingTools #Automation
Second day on Symbiote and things are clicking. Started with Phi3-mini (3.8B) for generating test steps decent, but too hit-or-miss for reliable automation🧐. Now pivoting to vision models so the agent can literally “see” the UI and act like a human tester. Tested LLaVA → instructions solid, vision still fuzzy on dense UIs. Today I am gonna give BakLLaVA & Moondream try. Drop your favorite open-source vision model below (bonus if <7B and actually good at UI screenshots).
Let’s crowd-source the best eyes for autonomous testing agents 👀
#AITesting #LocalFirst #OpenSourceAI #VisionModels #LLaVA #Moondream #BakLLaVA #TestingTools #IndieDev #BuildInPublic #WebDev #TypeScript #AI #Automation #Builders #Python
#AgenticAI journey with #Python update
Installed Docker, Ollama, LLaVA & OpenWebUI — sounds easy, but took 2 days of debugging chaos 😅
Ollama ran, OpenWebUI didn’t. Fixed one, broke another. Finally installed Ollama locally — smooth as butter! 🧈
#AI #Docker #LLaVA #Debugging
New tutorial! 🚀
Building a Streamlit Python UI for LLaVA with OpenAI API Integration
https://t.co/GqY3ikbipE 👍
Author: Vikram Singh
#LLaVA #vLLM #Streamlit #MultimodalAI #Python #LLMs #OpenAIAPI
New tutorial! 🚀
Setting Up LLaVA/BakLLaVA with vLLM
https://t.co/5kyW7bSfxb 👍
Author: Vikram Singh
#vLLM #LLaVA #BakLLaVA #MultimodalAI #ComputerVision #OpenAIAPI #HuggingFace #MLOps
New tutorial! 🚀
The Rise of Multimodal LLMs + vLLM
https://t.co/kvaRa6xtbf 👍
Author: Vikram Singh
#Multimodal #LLMs #vLLM #LLaVA #BakLLaVA #AI #MLOps #OpenSourceAI
Görme engelli vatandaşlar için LLaVA multimodelini kullanarak önündeki manzarayı seslendiren bir proje geliştiriyorum. Bu konuda "şunu da eklesen çok iyi olur" dediğiniz fikirleriniz varsa mutlaka beklerim :)
#yapayzeka #computervision #opencv #llava #multimodel
🚀 We just launched an alt-text bot on Bluesky!
This bot automatically generates alt-text for images using the @BacalhauProject + #LLaVa #LVM - making the web more accessible for everyone. 💡
It uses LVMs to generate the text - read our blog to learn more! (link in 🧵)
Let’s make the web more inclusive! ✨ #Accessibility #AltText #AI #Bluesky #Bacalhau
Can AI really predict how engaged you are while gaming? We put #GPT and #LLaVA to the test with 80 minutes of FPS gameplay and 2,400+ experiments!
Did they match human intuition or miss the mark? Watch our 1-min breakdown to find out! #AI #GameResearch #AffectiveComputing
Unlocking the synergy of CLIP, LLaVA, and the brain to revolutionize AI with human-like sensory integration.
#AI #HumanoidRobots #CLIP #LLaVA #Innovation #ArtificialIntelligence #TechForGood #FutureOfAI #HattussaITSolutions
@zilliz_universe @PaaSDev @FlatironSchool This is a very cool space with a view of Wall Street. Can't wait to show #Milvus #Ollama #LangChain #PyMilvus #MilvusLIte #VectorDatabase #UnstructuredData #LLava #CLIP #LLAMA
I just published Ghosts are Unstructured Data I https://t.co/BwEZmT8Ios
#Ghosts #UnstructuredData #Milvus
#CLiP #LLava
🔥 Today we are introducing LLaVA-MORE, a family of models that enhances #LLaVA by integrating #LLaMA 3.1 as the language model.
👉 Check out the repository at https://t.co/8wxezz2Jfp
F. Cocchi, N. Moratelli, D. Caffagni, @sarto_sara @marcella_cornia @ricucch
What if you give llava-llama3 vision into a computer desktop via screenshot images, some python library documentation and the objective to "open the web browser and google for pizza recipes without tomato"? 🧠🍕 #ai #llava #llama3 #multimodal
Is there any evidence that some #LLaVA versions can understand video *dynamics*? Most examples I've seen show outputs that might have inferred by static frames just as well
Parameter-free LLaVA for video captioning works like magic! 🤩
Let's take a look 🧶
(also find repositories below ⬇️ )
Last Seen Hashtags on Sotwe
Most Popular Users
Elon Musk 
@elonmusk
240.6M followers
Barack Obama
@barackobama
119.2M followers
Donald J. Trump
@realdonaldtrump
111.7M followers
Cristiano Ronaldo
@cristiano
110.6M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
97.6M followers
NASA
@nasa
92.2M followers
Justin Bieber
@justinbieber
90.9M followers
KATY PERRY
@katyperry
87.7M followers
Taylor Swift
@taylorswift13
81.5M followers
Lady Gaga
@ladygaga
73M followers
Virat Kohli
@imvkohli
69.9M followers
Kim Kardashian
@kimkardashian
69.8M followers
YouTube
@youtube
68.7M followers
Bill Gates
@billgates
63.9M followers
Neymar Jr
@neymarjr
62.6M followers
The Ellen Show
@theellenshow
62.4M followers
CNN
@cnn
61.9M followers
X
@x
60.8M followers
Selena Gomez
@selenagomez
60.7M followers