Overview The Condense Question mode is a simple chat mode built on top of a data query engine. It provides a flexible chat engine by compressing the conversation context and latest message into standalone questions, which are then interacted with the query engine. For each chat interaction: 1. First, generate a standalone question based on … Read more
Source: DeepHub IMBA This article is about 2500 words long and is recommended to be read in 5 minutes. This article will introduce the integration of LLMLingua with the proprietary LlamaIndex for efficient inference. The emergence of large language models (llm) has spurred innovation across multiple fields. However, with strategies driven by chain of thought … Read more
Scaling up: how increasing inputs has made artificial intelligence more capable The path to recent advanced AI systems has been more about building larger systems than making scientific breakthroughs. By: Veronika Samborska January 20, 2025 Cite this articleReuse our work freely For most of Artificial Intelligence’s (AI’s) history, many researchers expected that building truly capable … Read more
Last week, the “Huxiu Research” column under Huxiu updated its episode titled “Is Chinese Bound to Fall Behind in the AI Wave?” After the episode aired, we received discussions and doubts from various parties. The questions mainly fell into two categories: One category included many AI practitioners pointing out that our understanding of the principles … Read more
Source: Authorized reproduction from Machine Learning Algorithms and Python Practice Author: Lao Zhang is Busy Discovered an amazing Python library that makes creating large model applications incredibly simple. 8 lines of code is enough (with 2 optional lines). import gradio as gr import ai_gradio gr.load( name='qwen:qwen1.5-14b-chat', src=ai_gradio.registry, title='AI Chat', description='Chat with an AI model' ).launch() … Read more
1. Mistral and Microsoft’s Collaboration Recently, Microsoft announced a collaboration with Mistral AI, which has attracted considerable attention from industry insiders. The partnership focuses on three core areas: Supercomputing Infrastructure: Microsoft will support Mistral AI through Azure AI supercomputing infrastructure, providing top-tier performance and scale for the training and inference workloads of Mistral AI’s flagship … Read more
Cost is the invisible competitive advantage of large models. Author｜Liu Yangnan Editor｜Zhao Jian Today, the Tsinghua University-affiliated large model company “Mianbi Intelligent” released its first flagship large model “Mianbi MiniCPM”, which has been aptly named “Little Cannon”. According to Mianbi Intelligent’s co-founder and CEO Li Dahai, the parameter scale of Mianbi MiniCPM is 2B, using … Read more
▲ Click on the top Leiphone to follow Written by | AI Technology Review Report from Leiphone (leiphone-sz) Leiphone AI Technology Review notes: This article is an interpretation provided by Pan Shengfeng from Zhuiyi Technology based on Google’s paper for AI Technology Review. Recently, Google researchers achieved state-of-the-art results on 11 NLP tasks with the … Read more
Author: Prince Changqin (NLP Algorithm Engineer) Bert, Pre-training of Deep Bidirectional Transformers for Language Understanding Note Paper: https://arxiv.org/pdf/1810.04805.pdf Code: https://github.com/google-research/bert The core idea of Bert: MaskLM utilizes bidirectional context + MultiTask. Abstract BERT obtains a deep bidirectional representation of text by jointly training the context across all layers. Introduction Two methods to apply pre-trained models … Read more
Big Data Digest authorized repost from Data Party THU Author: Chen Zhiyan Twitter has always been an important source of news, and during the COVID-19 pandemic, the public has been able to express their anxieties on Twitter. However, manually classifying, filtering, and summarizing the massive amount of COVID-19 information on Twitter is nearly impossible. This … Read more