Apparently this is a 8x22B MoE (Mixture of Experts) model Mistral's previous most powerful openly licensed model was Mixtral, an 8x7B MoE
OPEN SOURCE
-
Day 2 Progress: 17 Hours Before Segfault Debugging Issues
By
–
Day 2. went 17 hours before dying again. progress here https://
gist.github.com/swyxio/d37350c
1061d39b38b103c8d0f1438c7#file-day_2_devin_train_gpt2-c
… its stuck debugging segfaults and memory errors and i'm not confident that it is making material progress. It may need a bit of hinting and direction – but i dont want to tell it to search the -
Gemini YouTube Researcher: AI Agent Analyzes Video Content
By
–
Introducing `gemini-youtube-researcher` 📈
— Matt Shumer (@mattshumer_) 10 avril 2024
An open-source Gemini 1.5 Pro agent that LISTENS to videos and delivers topical reports.
Just provide a topic, and a chain of AIs with access to YouTube will analyze relevant videos and generate a comprehensive report for you. pic.twitter.com/bd0OZkvCkqIntroducing `gemini-youtube-researcher` An open-source Gemini 1.5 Pro agent that LISTENS to videos and delivers topical reports. Just provide a topic, and a chain of AIs with access to YouTube will analyze relevant videos and generate a comprehensive report for you.
-
Datasette Extract Plugin: Data Extraction in Action
By
–
Blog post with screenshots of the plugin in action https://
datasette.cloud/blog/2024/data
sette-extract/
… -
Datasette Extract Plugin: Data Extraction Tool Showcase
By
–
Here's a blog post with further screenshots of the plugin in action: https://
datasette.cloud/blog/2024/data
sette-extract/
… -
RecurrentGemma Open Source: Griffin Achieves Inference Throughput Gains
By
–
I’m very proud of our team for open sourcing RecurrentGemma. Yes, recurrence is back and it results in huge gains at inference time. Just look at the impressive throughput plot below. For details, please see the paper and GitHub page: Griffin: Mixing Gated Linear Recurrences
-
Integrating Gradio with OpenCV DNN for Real-Time Web Applications
By
–
🚀 Blog-tastic Tuesdays 🚀https://t.co/CdPoepqAr1
— Satya Mallick (@LearnOpenCV) 9 avril 2024
Integrating Gradio with OpenCV DNN unlocks the answers to creating lightweight, efficient web applications that offer real-time inference capabilities. This combination leverages OpenCV’s robust deep-learning model inference… pic.twitter.com/Dh6zMih8rjBlog-tastic Tuesdays https://
learnopencv.com/integrating-gr
adio-with-opencv-dnn/
… Integrating Gradio with OpenCV DNN unlocks the answers to creating lightweight, efficient web applications that offer real-time inference capabilities. This combination leverages OpenCV’s robust deep-learning model inference -
MLX and Tinygrad: Open Source ML Frameworks in Complexity Phase
By
–
MLX is nice, early in its complexity phase.
also tinygrad. -
Multi-Agent Collaboration Boosts AI Performance Beyond Model Size
By
–
A new study from Cornell researchers just found that increasing the number of AI agents collaborating on a problem can significantly improve performance. Notably: A 13B parameter Llama model beat a 70B version on some tasks by scaling the number of agents up.
-
LLM Agents Challenge: Porting PyTorch GPT-2 Training to C
By
–
Btw writing the llm.c training code would imo be a very interesting, impressive, self-contained and very meta challenge for LLM agents. The prompt is: Take the PyTorch code train_gpt2.py
And write, compile and unit test a single .c file that reproduces the training: train_gpt2.c