如何使用RAG改进LLM
This article is part of a larger series on using large language models in practice. In the previous post, we fine-tuned Mistral-7b-Instruct to respond to YouTube comments using QLoRA.
如何制作RAG系统以获得对您数据的强大访问
A RAG system is an innovative approach to information retrieval. It utilizes traditional information retrieval approaches like vector similarity search combined with state-of-the-art large language model technology. Combined, these technologies make up a robust system that can access vast amounts of information from a simple prompt.
强化学习已经死了。Transformer万岁！
人工智能对科学进步的威胁：单一文化与知识的幻觉
While listening to a podcast called Weird Studies, I was struck by how the relentless drive to quantify and categorize the world leaves little room for the ‘weird’ — phenomena that d
陷入困境：乐高®人工智能艺术的崩溃比Willy Wonka人工智能灾难更糟糕
LEGO officially entered the AI art wars with a marketing misstep that’s worse than stepping on a Lego brick barefoot in the middle of the night.
使用Gemma 7B LLM和Upstash矢量数据库构建RAG应用程序
Retrieval-Augmented Generation (RAG) is the concept of providing large language models (LLMs) with additional information from an external knowledge source. This allows them to generate more accurate and contextual answers while reducing hallucinations.
100%开源Llama编码助手：再见，再见GPT-4！
All right, I’ve got something really exciting to share with you today!
We all know that coding assistants have permanently changed the way we approach developing software, but the hefty price tag of advanced LLMs like GPT-4 has been a stumbling block for many.
But here’s the fantastic news: Cost is no longer a barrier!
难以置信的使用此新技术在单个4GB GPU上运行70B LLM推理
Large language models require huge amounts of GPU memory. Is it possible to run inference on a single GPU? If so, what is the minimum GPU memory required?
The 70B large language model has parameter size of 130GB. Just loading the model into the GPU requires 2 A100 GPUs with 100GB memory each.
每一位人工智能/机器学习工程师都应该知道的第二代人工智能框架和工具！
In the rapidly evolving landscape of technology, Generative AI stands as a revolutionary force, transforming how developers & AI/ML engineers approach complex problems and innovate. This article delves into the world of Generative AI, uncovering frameworks and tools that are essential for every developer.
Gemini Ultra vs GPT-4：谷歌这次打败GPT-4了吗？
The good, bad, and unexpected of Gemini Ultra.
Google just released Gemini Advanced, which is powered by its most capable AI model Gemini Ultra.