Summary 66 Endnotes 68 Prompt Engineering February 2025 6 Introduction When thinking about a large language model input and output, a text prompt (sometimes accompanied by other modalities such as image sequence of tokens. Prompt engineering is the process of designing high-quality prompts that guide LLMs to produce accurate outputs. This process involves tinkering to find the best prompt, optimizing prompt’s writing style and structure in relation to the task. In the context of natural language processing and LLMs, a prompt is an input provided to the model to generate a response or prediction. Prompt

ever-growing digital datasets that have been in the making for over three decades; breakthrough large language models (LLMs) that – in effect – found freedom with the November 2022 launch of OpenAI’s ChatGPT with Momentum + China’s Rise 5 Leading USA LLMs vs. China LLM Desktop User Share Note: Data is non-deduped. Share is relative, measured across six leading global LLMs. Source: YipitData (5/25) Desktop User computers are ingesting massive datasets to get smarter and more competitive. Breakthroughs in large models, cost-per-token declines, open-source proliferation and chip performance improvements are making

Economical, and Efficient Mixture-of-Experts Language Model DeepSeek-AI research@deepseek.com Abstract We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models. The model checkpoints are available at h t t p s : / / g i t h u b . c o m / d e e p s e e k - a

foundations 7 Guardrails 24 Conclusion 32 2 Practical guide to building agents Introduction Large language models are becoming increasingly capable of handling complex, multi-step tasks. Advances in reasoning or generating a report. Applications that integrate LLMs but don’t use them to control workflow execution—think simple chatbots, single-turn LLMs, or sentiment classifiers—are not agents. More concretely security reviews. 03 Heavy reliance on unstructured data: Scenarios that involve interpreting natural language, 
 extracting meaning from documents, or interacting with 
 users conversationally, for example

Question Answering Dataset），这个数据集 是一个著名的问答数据集，基于维基百科数据生成，并且数 据是2020年之前的。 AI幻觉问题抽取：多数据集 问题加载 探讨大语言模型（LLMs）在模拟人类意见动态和社 会现象（如极化和错误信息传播）中的表现，特别 是引入偏误信息后的意见动态变化。使用大模型模 拟多个虚拟代理，讨论“气候变暖”、“转基因食 品的安全性”和“疫苗的有效性和安全性”三个具

evals 6 Embed AI into your products 9 Start now and invest early 11 Customize and fine-tune your models 13 Get AI in the hands of experts 16 Unblock your developers 18 Set bold automation goals 21 research and deployment company, OpenAI prioritizes partnering with global companies because our models will increasingly do their best work with sophisticated, complex, interconnected workflows and systems teams. Our Research Team advances the foundations of AI, developing new models and capabilities. Our Applied Team turns those models into products, like ChatGPT Enterprise and our API. And our Deployment

groundwork forimproved multi-language support for expPosing runtime, and |IRs. QQ octoML Unified Object Protocol vm::Object NDArray | Rd | tuplelclosure AST Nodes Cross language suppPort Easy to introduce remumn dming data AutoTYM 二 QQ octoML Coming Soon to HTVM (Self-Hosted Models) Host Device mized RE -一 一 QQ octoML Transformer Improvements Transformer based models such as BERT have recently become very Popular and require first class support in TVML. ee What

workloads and hardware Hardware FrameworksWhy Automation is the Future Clear winner on emerging models in product Competitive on benchmarking type model Quickly enables other optimizations: fusion Portable performance across devicesWhy Automation is the Future 1 1 1 1 0.76 0.83 1.16 1.44 Large MatMul BatchConv Small MatMul BatchMatMul CuDNN w/ TensorCores tvm w/ TensorCores 1.4x better on Dynamic shape workloads More runtime objects: Arrays, Tuples, Trees, ADTs Minimum runtime for dynamic models Credit: Jared Roesch, Haichen Shen et.aluTVM: TVM on bare-metal Devices Support bare-metal J-TAG

its Affiliates. All rights reserved. Animesh Jain Amazon SageMaker Neo Compilation of Quantized Models in TVM AWS AI© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Quantization dataset • Finds suitable quantization scale • Produces a quantized graph • Compiling Pre-quantized models – QNN Dialect • TVM ingests a pre-quantized graph in TFLite or MxNet • Use high-level wrapper ops Frontend Parsers • TFLite Pre-quantized Models • In good shape • Supports all Image Classification PreQuantized hosted models • MXNet Pre-quantized Models • Tested internally with MxNet + MKLDNN

Trademark Deploying GluonCV models using TVM© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Trademark Deploy GluonCV Models GluonCV Models MXNet Computational Graph Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Trademark Deploy GluonCV Models https://arxiv.org/pdf/1907.02154.pdf© 2019, Amazon Web Services, Inc. or its Affiliates. All rights