Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks paper page: https://
huggingface.co/papers/2306.04
009
… Despite readily memorizing world knowledge about entities, pre-trained language models (LMs) struggle to compose together two or more
MACHINE LEARNING
-
Multi-Hop Reasoning in Language Models via Soft Prompts
By
–
-
A Generation Defining AI Moment
By
–
A generation defining AI moment https://
bit.ly/3KtI64X #MachineLearning #AI #DataScience #DeepLearning -
M3IT: Large-Scale Multi-Modal Multilingual Instruction Tuning Dataset
By
–
M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning paper page: https://
huggingface.co/papers/2306.04
387
… Instruction tuning has significantly advanced large language models (LLMs) such as ChatGPT, enabling them to align with human instructions across diverse tasks. -
Generative AI: Education In The Age Of Innovation
By
–
Generative AI: Education In The Age Of Innovation
#AI #AIio #BigData #ML #NLU #Futureofwork @CRudinschi @AntonioSelas @alexjc @RobotLaunch @karpathy @andyjankowski @bobgourley @CadeMetz http://
ow.ly/J76330svHUu -
Self Query Technique Improves Retrieval in JavaScript
By
–
Self query is awesome technique for improving retrieval – glad to see it making its way to JS
-
Snorkel AI Conference Day 1 Wraps with Industry Leaders
By
–
As we wrap up Day 1 at https://
future.snorkel.ai, thank you to all attendees, speakers, and partners @microsoft
, @huggingface
, @gretal_ai, @seldon_io
, @predibase
, @togethercompute
, @LambdaAPI
. See you tomorrow for thought-provoking sessions as we dive deep into #datacentricai -
AlphaDev: Deep RL Breakthrough in LLVM C++ Standard Library
By
–
It took a lot of Deep RL finesse (& some Transformers ) to get the first change in over a decade accepted into the LLVM standard C++ library. AlphaDev, published @Nature by my brilliant colleagues!
-
H2O Meetup on Open Source LLMs and GPT in Seattle
By
–
Eager to learn more about #OpenSource #LLMs and #GPT? Join the @h2oai team for a #meetup on Thursday, June 22, from 6:00-8:00 pm at the Pioneer Collective in Seattle! Register now: http://
ow.ly/JYXa50OIs1O #h2ogpt #H2OLLMStudio #DemocratizeAI #GenerativeAI #machinelearning -
AI Agents Pipeline User Code Data ML Models LLMs MLOps
By
–
With our AI agents, you can pipeline: – any user code
– any data transformations
– ML models & LLM prompts and execute and monitor these pipelines on our SOTA MLOps platform. Check it out here – -
AI Discovers 70% Faster Sorting Algorithm Optimization
By
–
This is awesome. 70% faster on such a basic task of sorting that we all learn early on as programmers. Super exciting to see AI find major speed ups in algorithms and libraries we all rely on.