2020 - The Abacus.AI Blog
Tutorial| The Abacus.AI Blog
In the rapidly evolving world of technology, having a reliable coding assistant can significantly enhance your development experience. At Abacus.Ai, we proudly present the AI Engineer, a powerful tool developed by Chat LLM that serves... The post Introducing the AI Engineer: Your Personal Coding Assistant appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Today we release a new model in our continued commitment to improving the state-of-the-art in open source LLMs: MetaMath-Bagel-DPO-34B. This time, we’ve refined our focus on enhancing mathematical and reasoning capabilities in LLMs by primarily... The post Sharper LLMs: Enhancing Math and Reasoning Abilities appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Here at Abacus.AI, we are strong believers in the potential of open source LLMs. The gap in performance with the major commercial closed-sourced models has steadily been decreasing over the last 6 months, thanks to... The post Improving Open-Source LLMs – Datasets, Merging and Stacking appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
The Abacus.AI team has published five papers to appear at the Conference on Neural Information Processing Systems (NeurIPS) 2023. Three papers are in the main conference (including one awarded with an Oral Presentation) and two... The post Abacus.AI at NeurIPS 2023 appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Organizations want to infuse LLMs into every part of their planning and decision making process. This translates to thousands, if not millions of API calls a day. While GPT-4 is great, it’s also prohibitively expensive,... The post Open Source LLMs, Fine-Tunes and RAG Based Vector Store APIs appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
How does Amazon manage to flawlessly deliver millions of products across the globe every day? Or a restaurant chain accurately predict demand, plan inventory and distribute staff coverage across its footprint? The secret sauce is... The post Machine Learning Meets Optimization appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Today we release a larger 70B version of Giraffe, succeeding the 13B model we mentioned in a previous blog post. Giraffe is a family of models that are finetuned from base Llama 2 and use... The post Closing the Gap to Closed Source LLMs – 70B Giraffe 32k appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Every organization has tons of data but it’s always a challenge to find actionable insights from it. Much like finding a needle in the haystack, you have to look through tons of reports to discern... The post Data LLM: Get insights from your data appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Following up on the work from our previous blog post, we are releasing today an arXiv paper titled “Giraffe: Adventures in Expanding Context Lengths in LLMs”. Giraffe is a new family of models that are... The post Giraffe – Long Context LLMs appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
The launch of ChatGPT has created a pivotal moment, enabling enterprises to envision new use cases and accelerated the adoption of AI within these corporations. One such use case in the enterprise space is the... The post Create a CustomGPT And Supercharge your Company with AI – Pick the Best LLM appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
We have been working on various experiments related to extending the context of pretrained models. In the post we share links to a repository with code and hugging face models and datasets. The post Treating Attention Deficit Disorder in LLMs appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
In this blog post, we discuss Abacus.AI’s NeurIPS 2022 paper on recommender systems.Paper: https://arxiv.org/abs/2206.11886Code: https://github.com/naszilla/reczilla1 min video: https://www.youtube.com/watch?v=Eu8G3oNzcvU5 min video: https://www.youtube.com/watch?v=NkNdxF5chZY The concept of meta-learning is both simple and powerful: information about the past performance... The post On the Generalizability and Predictability of Recommender Systems appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
The Abacus.AI team has published two papers to appear at the Conference on Neural Information Processing Systems (NeurIPS) 2022. NeurIPS is a top machine learning conference held every December. Abacus.AI is also planning a social... The post Abacus.AI at NeurIPS 2022 appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
In our previous post, we presented an introduction to Seq2Seq models – models that take a sequence as an input and produce a sequence for their output. Back in 2014, they revolutionized the field of... The post Beginners Guide To Transformer Models appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
When reading about Machine Learning, the majority of the material you’ve encountered is likely concerned with classification problems. You have a certain input, and the ML model tries to figure out the features of that... The post Understanding Variational Autoencoders and Their Applications appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Anyone who’s worked in a manufacturing space can tell you that one of the most significant challenges they face is managing supply chains of the materials and speciality items used to fabricate products. Without clear foresight into demand, how, when and from where they’ll get these vital items, the manufacturing process can quickly become untenable. The post Solving A Hard AI Problem: Generating Forecasts In Sparse Data Environments! appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Abacus.AI’s service empowers all our developers and data scientists to rapidly create powerful deep learning models at scale, in production. We can optimize all aspects of our user experience including personalizing emails, predictive churn and providing contextual real-time recommendations. This translates a lift in both user-engagement and revenue. The post Becoming An AI First Organization: The 1-800-Flowers Journey appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Today, we at Abacus.AI are thrilled to announce our Series A funding and Mike Volpi and Ram Shriram as Board Directors. In addition, we are open-sourcing our debiasing module. In this post, we give an introduction to bias in computer vision models and discuss our new research on debiasing models. The post Debiasing Facial Prediction Models with Adversarial Fine-Tuning appeared first on The Abacus.AI Blog.| The Abacus.AI Blog
Most of the machine learning applications are concerned with processing data such as images or databases – their key characteristic is that they can be “taken in” by a learning model all at once. They don’t have any temporal properties. Today we’ll be talking about a different case – models that deal with data that is sequential by nature, text, and voice being several examples.| The Abacus.AI Blog
Abacus.AI is the world's first end-to-end MLOps and AI platform that enables real-time machine and deep learning at scale for common enterprise use cases.| The Abacus.AI Blog
The pursuit of automating mundane tasks and boosting productivity has long been a priority for executives. In the past couple of decades, significant progress has been made in developing tools to automate tasks that follow...| The Abacus.AI Blog
