1. Title: KIMI K1.5: SCALING REINFORCEMENT LEARNING WITH LLMS Link: https://github.com/MoonshotAI/kimi-k1.5 2. Authors and Key Points: 1- Authors The paper was published by: Kimi Team of the Dark Side of the Moon 2- Key Points 1. Core Content • Background and Motivation: • Traditional language model pre-training methods (based on next-word prediction) perform well in … Read more
Thank you for reading. I am Jiang Feng, focusing on AI tools, intelligent agents, and AI programming. Follow our public account to receive a big gift package, including AI/Python/eBooks materials. There are benefits at the end of the article. The domestic large model Deepseek has successfully attracted the attention of AI tech leaders worldwide. Recently, … Read more
Yesterday, everyone was shouting about the New Year! Kimi has released a rare technical report, let’s take a look at the technical details. The technical report is here: https://github.com/MoonshotAI/Kimi-k1.5 First, as always, Kimi emphasizes long context. So the question arises: if we provide the model with a longer ‘thinking space’, can it naturally learn to … Read more
Technical Overview From LLaMA1 to LLaMA3.3 CloseMoreName clearedScan to Appreciate the Author on WeChatLike the AuthorOther AmountArticlesNo articlesLike the AuthorOther Amount¥Minimum Appreciation ¥0OKBackOther AmountMoreAppreciation Amount¥Minimum Appreciation ¥01234567890. , January 14, 2025 01:00 , ,
Llama 3.2 Reasoning WebGPU: A compact and powerful reasoning language model that runs in the browser, akin to putting an intelligent brain into a webpage, enabling quick understanding and reasoning of various issues. References: [1] http://github.com/huggingface/transformers.js-examples/tree/main/llama-3.2-reasoning-webgpu Welcome to support my knowledge platform (NLP Engineering): Dify source code analysis and Q&A, Dify dialogue system source code, … Read more
Meow! In the previous article, we used Tongyi Qianwen to create an intelligent customer service agent with four major functions through four system-level prompts. This article will build an upgraded agent based on calling Tongyi Qianwen and combining it with Llama-Index. First, let’s implement the simplest example using ReActAgent and Functional Tool to create a … Read more
With the rapid development of large model technology, how to fully utilize AI while ensuring data privacy has become a hot topic. Open-source local large language models (LLMs) are gradually becoming an important tool to solve this problem. Today, we will introduce a star-level open-source model—LLaMA2, and see how it seamlessly implements the “text to … Read more
Follow the official account above to reply:Course Resources can be obtained from this course There is a course on Tang Guoliang Llama model architecture from theory to practice Tang Guoliang Llama model architecture from theory to practice Tang Guoliang Llama Model Architecture: From Theory to Practice In today’s era of rapid advancement in artificial intelligence, … Read more
Are you still troubled by the mixed quality and poor performance of domestic AI? Then let’s take a look at Dev Cat AI (3in1)! This is an integrated AI assistant that combines GPT-4, Claude3, and Gemini. It covers all models of these three AI tools. Including GPT-4o and Gemini flash Now you can own them … Read more
Are you still troubled by the uneven quality and poor performance of AI in China? Then let’s take a look at Dev Cat AI (3in1). This is an integrated AI assistant that combines GPT-4, Claude3, and Gemini. It covers all models of the three AI tools. Including GPT-4o and Gemini flash Now you can own … Read more