OpenGPTs YouTube walkthrough A proper deep dive into OpenGPTs! Covers two main things: How to use the hosted version
Walkthrough of the code that powers the backend https://
youtube.com/watch?v=HAn9vn
Jy6S4
…
OPEN SOURCE
-
OpenGPTs YouTube Walkthrough: Hosted Version and Backend Code
By
–
-
Tenstorrent Open Sources TT-Metalium Kernel Software Stack
By
–
We're excited to announce that we have open sourced our kernel-level software stack, TT-Metalium. @ojoyoshida sat down with @DavidBennett__ and #tenstorrent fellow Jasmina Vasiljevic to talk #opensource, #software and our Grayskull DevKit https://
ojoyoshidareport.com/if-nvidia-is-a
i-hardwares-goliath-wheres-david/
… -
Early Access Model Leaked: Company Retrains from Llama 2
By
–
An over-enthusiastic employee of one of our early access customers leaked a quantised (and watermarked) version of an old model we trained and distributed quite openly. To quickly start working with a few selected customers, we retrained this model from Llama 2 the minute we got
-
OpenGPTs Updates: Open Source AI Model Control Tools
By
–
OpenGPTs Updates Some big updates to OpenGPTs! Reminder: OpenGPTs is an open source version of the GPT store where you can fully control the model used, the tools used, the retrieval strategy Blog + YouTube to dive into more detail! What are the updates? LangGraph:
-
Drupal Receives $300K Sustainable Funding for Security Projects
By
–
Drupal just celebrated its 23rd birthday! What better gift than sustainable open source funding? @sovtechfund has generously provided @drupalassoc $300,000 to fuel two crucial projects that promise to strengthen security for Drupal and enhance the Drupal ecosystem.
-
Community Manager Leaves Amplication After Developer Relations Role
By
–
Every good thing comes to an end! Today is my last day as a Community Manager at @amplication
. It was my first Developer Relations job and I worked on amazing things that impacted the wider open source developer community. Excited for the new adventures -
RAG Encoder and Reranker Evaluation with Open-Source Models
By
–
Inspired by @ravithejads
, wrote a simple blog post on "RAG – Encoder and Reranker evaluation" using @llama_index on a custom QA dataset. Used open-source embeddings and re-rankers for the evaluation
"JinaAI-base" embedding with "bge-reranker-large" gave the best result among -
Code Llama 70B Achieves 67.8 HumanEval Score
By
–
Code Llama 70B scores a 67.8 on HumanEval, making it one of the highest performing open models available today. Happy hacking!
-
Code Llama 70B Base: The Foundational Code Model
By
–
And Code Llama 70B base is the foundational code model: