LLMS - AI Dynamics

LongNet: Scaling Transformers to Handle Billion Tokens

By

–

06 July 2023 4h14

LongNet: Scaling Transformers to 1,000,000,000 Tokens paper page: https://
huggingface.co/papers/2307.02
486
… Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity,

→ View original post on X — @_akhaliq

6 July 2023

Open-Source LLMs Match ChatGPT Performance in Text Annotation Tasks

By

@_akhaliq

–

06 July 2023 3h51

Open-Source Large Language Models Outperform Crowd Workers and Approach ChatGPT in Text-Annotation Tasks paper page: https://
huggingface.co/papers/2307.02
179
… study examines the performance of open-source Large Language Models (LLMs) in text annotation tasks and compares it with proprietary

→ View original post on X — @_akhaliq

6 July 2023

Building Cooperative Embodied Agents with Large Language Models

By

@_akhaliq

–

06 July 2023 3h40

Building Cooperative Embodied Agents Modularly with Large Language Models

paper page: https://t.co/QGisKj2HWc

Large Language Models (LLMs) have demonstrated impressive planning abilities in single-agent embodied tasks across various domains. However, their capacity for planning… pic.twitter.com/cajVGEH6zq
— AK (@_akhaliq) 6 juillet 2023

Building Cooperative Embodied Agents Modularly with Large Language Models paper page: https://
huggingface.co/papers/2307.02
485
… Large Language Models (LLMs) have demonstrated impressive planning abilities in single-agent embodied tasks across various domains. However, their capacity for planning

→ View original post on X — @_akhaliq

6 July 2023

Jailbroken: How Does LLM Safety Training Fail?

By

@_akhaliq

–

06 July 2023 3h37

Jailbroken: How Does LLM Safety Training Fail? paper page: https://
huggingface.co/papers/2307.02
483
… Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of "jailbreak" attacks on early releases of ChatGPT that elicit

→ View original post on X — @_akhaliq

6 July 2023

Flacuna: Enhancing Vicuna Problem-Solving with FLAN Fine-Tuning

By

@_akhaliq

–

06 July 2023 3h33

Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning paper page: https://
huggingface.co/papers/2307.02
053
… Recently, the release of INSTRUCTEVAL has provided valuable insights into the performance of large language models (LLMs) that utilize encoder-decoder or

→ View original post on X — @_akhaliq

6 July 2023

ETH Zürich DLSC Course Introduction

By

@miketamir

–

06 July 2023 3h01

ETH Zürich DLSC: Course Introduction https://
bit.ly/3qTjAUD #AI #MachineLearning #DeepLearning #LLMs #DataScience

→ View original post on X — @miketamir

6 July 2023

Recommendation for RLHF Technical Tutorial

By

@rasbt

–

06 July 2023 2h24

Great collection! And after the technical tutorials, I can highly recommend “How RLHF actually works”

→ View original post on X — @rasbt

6 July 2023

Improving Search Results with Cohere’s Reranking Techniques

By

@cohere

–

06 July 2023 1h03

Traditional search methods sometimes struggle to rank results effectively. But this can be improved using reranking techniques. In this article, we’ll go through a demo of using Cohere’s Rerank endpoint to boost Wikipedia’s search results. https://
short.cohere.ai/kGh0EW?utm_sou
rce=twitter&utm_medium=social
…

→ View original post on X — @cohere

6 July 2023