Agree, sharing different agent architectures could be cool What is right devx for this? Python packages? Remote hosted graphs?
OPEN SOURCE
-
Together AI, Fireworks AI, and Groq Lead Open LLM Deployment Innovation
By
–
"Companies like Together AI, Fireworks AI, and Groq are emerging players that focus on making it easier to deploy, scale and optimize open LLMs. Their tools and platforms streamline the deployment process, improving scalability." — @julianeagu / @Forbes https://
hubs.la/Q02VTTpK0 -
Pangea: Open Multilingual Multimodal LLM for 39 Languages
By
–
Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages
—————————–
Paper: https://
arxiv.org/abs/2410.16153
Project website: https://
neulab.github.io/Pangea/
Model: https://
huggingface.co/neulab/Pangea-
7B
…
Extended post by @xiangyue96 : -
Open Source AI Project Code Available for Experimentation
By
–
But, it’s open – with all the code open source, you can fiddle with it, try different prompts, things etc The final output is not at that level, but, it only gets better from here,
-
IBM Granite 3.0 Lightweight Foundation Models for Enterprise
By
–
7). Granite 3.0 – presents lightweight foundation models ranging from 400 million to 8B parameters; supports coding, RAG, reasoning, and function calling, focusing on enterprise use cases, including on-premise and on-device settings.
-
Aya Expanse: Multilingual Foundation Models 8B and 32B Parameters
By
–
2). Aya Expanse – a family of open-weight foundation models for multilingual capabilities; releases an 8B and 32B parameter model, including one of the largest multilingual dataset collections to date, with 513 million examples… https://t.co/LWH49PJKZ0
— DAIR.AI (@dair_ai) 27 octobre 20242). Aya Expanse – a family of open-weight foundation models for multilingual capabilities; releases an 8B and 32B parameter model, including one of the largest multilingual dataset collections to date, with 513 million examples…
-
AI NFT Genesis: Prior Art and DAO Vision 2017
By
–
[ PRIOR ART ] PATENT INVALIDATION “The AI NFT Genesis & Beyond” In the realm of #AI and #Blockchain, innovation speaks louder than threats! Proud to have shared the AI DAO vision at a public event back in 2017 (!) : https://
youtube.com/watch?v=Y4_6aZ
bVlo4
… #OpenAIGym #AINFT #NFT -
Build Fast Multi-Modal Apps with Groq and Gradio
By
–
Build fast multi-modal apps on @Gradio
, Powered by Groq! Using Whisper & Llama-3.2-vision, your end product will enable voice to text to LLM response, image to text & traditional chat. Check out @BenjaminKlieger's tutorial & repo at https://
hubs.la/Q02VzJmQ0 -
Llama PDF Pre-Processing Logic Guide Released
By
–
You can find it here: https://
github.com/meta-llama/lla
ma-recipes/blob/main/recipes/quickstart/NotebookLlama/Step-1PDF-Pre-Processing-Logic.ipynb
… -
Open Source AI Stack: Swappable Domain-Specific Models
By
–
Beauty of open source: You can replace any part of this stack drop-in with domain specific/ fine-tuned/ better models too.
— Vaibhav (VB) Srivastav (@reach_vb) 27 octobre 2024
Open intelligence. https://t.co/7b8e5bWxAZ pic.twitter.com/kqbvMyGqEjBeauty of open source: You can replace any part of this stack drop-in with domain specific/ fine-tuned/ better models too. Open intelligence.