Akmmus AIblog.akmmusai.pro·Mar 8, 2024A Survey of AI-generated Text Forensic SystemsTLDR - Along with remarkable text generation capabilities, LLMs pose serious risks like facilitating the spread of propaganda, misinformation, and disinformation at an alarming scale. In response to these dangers, a new field is rapidly developing ca...DiscussLLM's
Akmmus AIblog.akmmusai.pro·Mar 8, 2024Not all Layers of LLMs are Necessary during Inference (Short Summary)It is observed that during LLM inference, only a few layers are actively used. TLDR - The inference stage of LLMs being computationally expensive poses problems for real-time application use. During LLM inference, not every layer within an LLM is alw...Discussllm
Akmmus AIblog.akmmusai.pro·Mar 8, 2024Birbal: An efficient 7B instruct-model (Short Summary)TLDR - Birbal LLM is based on the Mistral-7B architecture and fine-tuned in 16 hours on a single RTX 4090 GPU. BirBal LLM outperformed the Qwen-14B model by a significant 35%. BirBal LLM’s success can be attributed to focused, high-quality instructio...Discussllm
Akmmus AIblog.akmmusai.pro·Mar 7, 2024SaulLM-7B: A pioneering Large Language Model for Law (short summary)TLDR - SaulLM-7B is a large language model (LLM) specifically designed to understand and generate legal text. It is based on the Mistral 7B LLM. SaulLM-7B was trained on a massive dataset of English legal documents (over 30 billion tokens). SaulLM-7B...Discuss·119 readsLLM's
Akmmus AIblog.akmmusai.pro·Mar 7, 2024Apollo: Lightweight Multilingual Medical LLMs towards Democratizing Medical AI to 6B People (short summary)TLDR - Multilingual medical LLMs (Apollo) are being developed to improve healthcare access in regions with limited resources and non-English speakers. These small, powerful models achieve state-of-the-art performance and will be openly available for ...Discuss·67 readsLLM's
Akmmus AIblog.akmmusai.pro·Mar 6, 2024The Era of 1-bit LLMs (Paper Summary)Abstract BitNet model introduced in 2023 initiated the era of 1-bit LLMs. This model marks a significant shift away from traditional, high-precision, computationally expensive LLMs to low-precision and cost-effective LLMs. BitNet b1.58 is a new 1-bit...Discuss·1 like·125 readsLLM's
Karthikeya Sarrajukarthikeyasarraju.hashnode.dev·Mar 4, 2024Introduction to Generative AIWelcome to the first day of our journey into Generative AI! Today, we're diving into a fascinating aspect of artificial intelligence that's not just about analyzing data, but about creating something new and innovative. Generative AI is a frontier in...Discussgenerative ai
S7VEN Qis7vencode.hashnode.dev·Mar 3, 2024Introducing The Concept Of Adaptive Language Evolution (ale)ABSTRACT: This research proposal explores the concept of ADAPTIVE LANGUAGE EVOLUTION (ALE), a novel approach to advancing the capabilities of language models through personalized memory and knowledge extraction from past interactions. We argue that A...DiscussMachine Learning
Pinak Dattapinakdatta.hashnode.dev·Mar 1, 2024FeaturedBuilding a Chatbot from Scratch using Rasa Framework: A Comprehensive GuideIntroduction: In today’s digital landscape, chatbots have become essential tools for businesses to enhance customer service and engagement. Among the various frameworks available, Rasa stands out for its flexibility and open-source nature. This guide...Discuss·14 likes·237 readsPython
Nguyen Thuy Linhlinkie.hashnode.dev·Mar 1, 2024Meta AI's Llama: A Comprehensive Guide to the Next Generation of Natural Language ProcessingAccording to a report by The Information, Meta plans to launch a new AI language model, Llama 3, in July, which would give better responses to contentious user questions. Meta researchers are trying to "loosen up" the model so that it could at least ...DiscussAI