#DBRX sets a new standard for efficient open source LLMs. While it has 132B total parameters, with its fine-grained MoE architecture, DBRX only uses 36B at any given time. Learn more about how we built #DBRX & benchmarked its performance. https://
dbricks.co/3J13hed
MACHINE LEARNING
-
DBRX: New Efficient Open Source LLM Standard
By
–
-
Shuffling Within Batch in Contrastive Learning Practices
By
–
well i do shuffle; it's not standard to shuffle *within the batch*, for contrastive learning
-
DBRX: New Open Source Model Beats Grok and Competition
By
–
Scoop: Grok had a good run but there’s a new open source model that beats out the rest: DBRX. I got an inside look at the impressive work that went into building it:
-
Data Science vs AI vs Machine Learning: 2024 Demand Comparison
By
–
#DataScience vs #AI vs #MachineLearning- What 2024 demand for?
by @DataScienceDojo Learn more: https://
buff.ly/4bsDloS #DataScientists #ArtificialIntelligence #MI #MI cc: @ravikikan @yvesmulkers @kuriharan -
Pollen Robotics Reachy: Advanced AI-Powered Robotics Innovation
By
–
This is pollen #Robotics Reachy
— Ronald van Loon (@Ronald_vanLoon) 27 mars 2024
by @IntEngineering#AI #ArtificialIntelligence #MI
cc: @dirkschaar @space_mog @maxjcm pic.twitter.com/0t0Jh77OANThis is pollen #Robotics Reachy
by @IntEngineering #AI #ArtificialIntelligence #MI cc: @dirkschaar @space_mog @maxjcm -
AI-Based Recommendation Systems Transforming E-commerce
By
–
How #AI-Based Recommendation Systems Are Transforming E-commerce
by @ONPASSIVE Learn more: https://
buff.ly/3SSu036 #ArtificialIntelligence #Chatbots #CX #CustomerExperience cc: @pascal_bornet @yvesmulkers @kuriharan -
Training Techniques for AI Layer Alignment with Tokens
By
–
Yeah, and then training on like 10 million tokens to align the layers
-
Merging Mistral-7B Models into Mistral-70B: Feasibility and Use Cases
By
–
I kinda want to make a Mistral-70B by frankenmerging 10 Mistral-7Bs together. Would anyone find this useful?
-
Fine-tuning requires robust evaluation systems to be effective
By
–
"It’s impossible to fine-tune effectively without an eval system which can lead to writing off fine-tuning if you haven't completed this prerequisite." That sounds spot-on to me. Eval systems still feel like a dark art, which would explain why I don't find fine-tuning attractive
-
Intelligent Robots Operating American Farm Efficiently
By
–
This American farm is run by intelligent #Robots
— Ronald van Loon (@Ronald_vanLoon) 27 mars 2024
by @wef#MI #Robotics #RPA #Innovation #AI #MachineLearning
cc: @pbalakrishnarao @chr1sa pic.twitter.com/iAYbYlEEZ1This American farm is run by intelligent #Robots
by @wef #MI #Robotics #RPA #Innovation #AI #MachineLearning cc: @pbalakrishnarao @chr1sa