Bonus session on KV Cache, Tooling and WMDP

• SlideDeck: W15-KVcahe-WMDP-Tools
• Version: current

Efficiency Safety

KV Caching in LLM:

• grouped query attention: https://arxiv.org/pdf/2305.13245.pdf
• Paged attention https://arxiv.org/pdf/2309.06180.pdf https://openreview.net/pdf?id=uNrFpDPMyo

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

• Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D. Li, Ann-Kathrin Dombrowski, Shashwat Goel, Long Phan, Gabriel Mukobi, Nathan Helm-Burger, Rassin Lababidi, Lennart Justen, Andrew B. Liu, Michael Chen, Isabelle Barrass, Oliver Zhang, Xiaoyuan Zhu, Rishub Tamirisa, Bhrugu Bharathi, Adam Khoja, Zhenqi Zhao, Ariel Herbert-Voss, Cort B. Breuer, Andy Zou, Mantas Mazeika, Zifan Wang, Palash Oswal, Weiran Liu, Adam A. Hunt, Justin Tienken-Harder, Kevin Y. Shih, Kemper Talley, John Guan, Russell Kaplan, Ian Steneker, David Campbell, Brad Jokubaitis, Alex Levinson, Jean Wang, William Qian, Kallol Krishna Karmakar, Steven Basart, Stephen Fitz, Mindy Levine, Ponnurangam Kumaraguru, Uday Tupakula, Vijay Varadharajan, Yan Shoshitaishvili, Jimmy Ba, Kevin M. Esvelt, Alexandr Wang, Dan Hendrycks
• The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs. However, current evaluations are private, preventing further research into mitigating risk. Furthermore, they focus on only a few, highly specific pathways for malicious use. To fill these gaps, we publicly release the Weapons of Mass Destruction Proxy (WMDP) benchmark, a dataset of 4,157 multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. WMDP was developed by a consortium of academics and technical consultants, and was stringently filtered to eliminate sensitive information prior to public release. WMDP serves two roles: first, as an evaluation for hazardous knowledge in LLMs, and second, as a benchmark for unlearning methods to remove such hazardous knowledge. To guide progress on unlearning, we develop CUT, a state-of-the-art unlearning method based on controlling model representations. CUT reduces model performance on WMDP while maintaining general capabilities in areas such as biology and computer science, suggesting that unlearning may be a concrete path towards reducing malicious use from LLMs. We release our benchmark and code publicly at this https URL

Must know tools for training/finetuning/serving LLM’s -

1. Torchtune - Build on top of Pytorch, for training and finetuning LLM’s. Uses yaml based configs for easily running experiments. Github -

2. axolotl - Built on top on Huggigface peft and transformer library, supports fine-tuning a large number for models like Mistral, LLama etc. Provides support for techniques like RLHF, DPO, LORA, qLORA etc. Github

3. LitGPT - Build on nanoGPT and Megatron, support pre-training and fine-tuning, has examples like Starcoder, TinyLlama etc. Github -

4. Maxtext - Jax based library for training LLM’s on Google TPU’s with configs for models like Gemma, Mistral and LLama2 etc. Github

5. Langchain- https://python.langchain.com/docs/get_started/introduction

6. haystack.deepset.ai
   • https://github.com/deepset-ai/haystack
   • LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it’s best suited for building RAG, question answering, semantic search or conversational agent chatbots.
7. LlamaIndex
   • https://docs.llamaindex.ai/en/stable/ LlamaIndex supports Retrieval-Augmented Generation (RAG). Instead of asking LLM to generate an answer immediately, LlamaIndex: retrieves information from your data sources first, / adds it to your question as context, and / asks the LLM to answer based on the enriched prompt.
8. Making Retrieval Augmented Generation Fast
   • https://www.pinecone.io/learn/fast-retrieval-augmented-generation/
9. OpenMoE
   • https://github.com/XueFuzhao/OpenMoE

More readings

Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond

• Jingfeng Yang, Hongye Jin, Ruixiang Tang, Xiaotian Han, Qizhang Feng, Haoming Jiang, Bing Yin, Xia Hu

• This paper presents a comprehensive and practical guide for practitioners and end-users working with Large Language Models (LLMs) in their downstream natural language processing (NLP) tasks. We provide discussions and insights into the usage of LLMs from the perspectives of models, data, and downstream tasks. Firstly, we offer an introduction and brief summary of current GPT- and BERT-style LLMs. Then, we discuss the influence of pre-training data, training data, and test data. Most importantly, we provide a detailed discussion about the use and non-use cases of large language models for various natural language processing tasks, such as knowledge-intensive tasks, traditional natural language understanding tasks, natural language generation tasks, emergent abilities, and considerations for specific tasks.We present various use cases and non-use cases to illustrate the practical applications and limitations of LLMs in real-world scenarios. We also try to understand the importance of data and the specific challenges associated with each NLP task. Furthermore, we explore the impact of spurious biases on LLMs and delve into other essential considerations, such as efficiency, cost, and latency, to ensure a comprehensive understanding of deploying LLMs in practice. This comprehensive guide aims to provide researchers and practitioners with valuable insights and best practices for working with LLMs, thereby enabling the successful implementation of these models in a wide range of NLP tasks. A curated list of practical guide resources of LLMs, regularly updated, .

• https://github.com/Mooler0410/LLMsPracticalGuide

Retentive Network: A Successor to Transformer for Large Language Models

• In this work, we propose Retentive Network (RetNet) as a foundation architecture for large language models, simultaneously achieving training parallelism, low-cost inference, and good performance. We theoretically derive the connection between recurrence and attention. Then we propose the retention mechanism for sequence modeling, which supports three computation paradigms, i.e., parallel, recurrent, and chunkwise recurrent. Specifically, the parallel representation allows for training parallelism. The recurrent representation enables low-cost $O(1)$ inference, which improves decoding throughput, latency, and GPU memory without sacrificing performance. The chunkwise recurrent representation… Show more

RWKV: Reinventing RNNs for the Transformer Era

• Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit linear scaling in memory and computational requirements but struggle to match the same performance as Transformers due to limitations in parallelization and scalability. We propose a novel model architecture, Receptance Weighted Key Value (RWKV), that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. Our approach leverages a linear attention mechanism and allows us to formulate the model as either a Transfor… Show more

Blog: