Speculative RAG splits Retrieval Augmented Generation tasks into two separate steps of drafting followed by verification to provide high-quality answer candidates, and substantially improve the quality and speed of the final output generation. Learn more →
CODE
-
Building AI Applications with Haystack: New Short Course
By
–
Build and customize complex AI applications with a flexible framework in this new short course, Building AI Applications with Haystack. Created in collaboration with @deepset_ai, and taught by @tuanacelik, who is the developer relations lead for Haystack at deepset.
— Andrew Ng (@AndrewYNg) 21 août 2024
Generative… pic.twitter.com/wqeTGILOx7Build and customize complex AI applications with a flexible framework in this new short course, Building AI Applications with Haystack. Created in collaboration with @deepset_ai
, and taught by @tuanacelik
, who is the developer relations lead for Haystack at deepset. Generative -
Llama 3.1 Fine-tuning: Code Allocation Breakdown
By
–
Yes, this is standard for general-purpose fine-tuning. Llama 3.1 uses 17% of code for pretraining and 14.89% for post-training.
-
Code in Pretraining Data Improves Model Performance
By
–
Nice paper from @Cohere about the impact of code in the pretraining data: • Including code improves performance on non-code tasks. It would be nice to see the effect on math benchmarks. [1] • Optimal proportion is around 25% but there's not a lot of data points: what about
-
Licensing Models: Proprietary vs Open Source AI Code
By
–
Please use your brain for a second longer! They are giving *licenses* that could end at any time, leaving those people in worse position than before. If the profit-seeking companies made a lite version of their code available forever on open-devices, it'd be fine…
-
Speculative Decoding State of the Art Paper Club Discussion
By
–
This is entirely speculative but… Tomorrow's LS paper club with @picocreator is going to be extremely lit! come learn about the state of the art in Speculative Decoding!
-
NASA Satellite Data Stream Analysis with Databricks Kafka
By
–
A journey in space with Databricks 🚀
— Databricks (@databricks) 20 août 2024
In this technical walkthrough, analyze a live data stream from NASA satellites using the Databricks Data Intelligence Platform and Apache Kafka. @frankmunz shows you how: https://t.co/m9YpczM8v4 pic.twitter.com/Bp0ypooOP3A journey in space with Databricks In this technical walkthrough, analyze a live data stream from NASA satellites using the Databricks Data Intelligence Platform and Apache Kafka. @frankmunz shows you how: https://
dbricks.co/3yW2Ro5 -
Cohere API Challenge at Hack the North 2024 Hackathon
By
–
Cohere is heading to Hack the North 2024, Canada's largest hackathon! We're hosting an API challenge with a workshop, offering a chance to win prizes. Meet our team, try our demo, and grab some swag.
-
Fall 2024 Draft Chapters Released for Speech and Language Processing
By
–
It's back-to-school time and so here's the Fall '24 release of draft chapters for Speech and Language Processing! web.stanford.edu/~jurafsky/s…
-
Domino Simplifies LLM Training with Ray Support
By
–
Domino simplifies and accelerates training complex LLMs. Using native Ray support and pre-built reference projects, teams can fine-tune Llama 70B without understanding the specifics or topology of hardware or infrastructure! See for yourself in this demo! https://
domino.buzz/4dMwAib