LLMs are very good at information retrieval and organization at scale. Systems that combine web search and LLMs make powerful tools that can educate us on any topic. Building a system is a non-trivial task featuring many complex components (see below for all of them). Platforms
@abacusai
-
Smaug-72B Tops Hugging Face Leaderboard as Best Open-Source Model
By
–
Two weeks ago we released Smaug-72B – which topped the Hugging Face LLM leaderboard and it’s the first model with an average score of 80, making it the world’s best open-source foundation model. We applied several techniques on a fine tune derived from a Qwen-72B for this model.
-
The Importance of Anomaly Detection in Security and Manufacturing
By
–
The Importance of Anomaly Detection Systems that detect anomalies are very critical in areas like security and manufacturing. There are a variety of ways to detect anomalies and platforms like Abacus AI have a wide selection at scale. An interesting use-case of this is
-
Free Webinar on LLM Landscape and AI Platform Demo
By
–
Our free webinar is tomorrow! Come listen to Bindu Reddy give an informative talk about the current LLM and AI landscape and learn how to use our state of the art ML and LLM Ops platform. We’ll build RAG systems, ChatLLMs, & AI agents – all complex AI systems for your
-
Building AI Agents Over Structured and Unstructured Data with LLMOps
By
–
Building AI agents over structured and unstructured data involves several components – like connecting your data sources, using your chosen LLM, and creating the agent that will automate many processes. LLMOps platforms like us at Abacus AI can accomplish this in a couple of
-
Abacus AI Open-Sources Advanced 30B Mathematical Reasoning Model
By
–
Open-Sourcing the World’s Smartest ~30B Model At Abacus AI we recently open-sourced the smartest ~30B in the world – MetaMath-Bagel_DPO-34B. Our primary docs were enhancing mathematical & reasoning capabilities in LLMs by improving the GSM8k scores. Our strategies involve data
-
Free RAG Systems and AI Agents Webinar Next Week
By
–
Our free RAG systems, Chat LLMs, and AI Agents webinar is back next week. @bindureddy will kick-off with an exciting discussion about current developments within the LLM landscape before we provide a preview of our state-of-the-art ML and LLMOps platform. If you want to learn
-
FuseLLM: Advancing Multi-Model LLM Combination with Probabilistic Approach
By
–
A couple weeks ago, we open-sourced a merged and stacked LLM, which is combining multiple pre-trained LLMs to come up with a new, more performant model. FuseLLM takes this to the next level and explores combining models from a probabilistic distribution perspective. The paper
-
Vector Embeddings: Essential for LLM Applications and Real-Time Retrieval
By
–
The popularity of LLMs has made vector embeddings popular and useful. You have to create embeddings for all of your data; whether that is text, speech or a mixture of both. With these embeddings, you also want the ability to retrieve them and send it to an LLM in real time.
-
Custom LLM and AI Agents for Structured and Unstructured Data
By
–
An AI Brain for your organization – custom LLM and AI Agents (RAG) on Structured + Unstructured Data Imagine having a ChatGPT-like interface over all your structured (database) and unstructured data. You can ask a question to an AI bot, and it can run multiple parallel queries,