I find it fascinating to see input vs output, and how tiny tweaks change things. Also since these things are so new there aren’t well established norms so I think people are curious to see how others structure prompts?
LLMS
-
ChatGPT for Data Science Cheat-Sheet Guide
By
–
#ChatGPT for #DataScience Cheat-Sheet! @kdnuggets #BigData #Analytics #AI #MachineLearning #IoT #IIoT #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding #100DaysOfCode https://
geni.us/ChatGPT-DSci -
Representing Complex Sentence Structure in NLP Systems
By
–
I am talking about how we represent eg complex sentences in terms of their parts.
-
Discover Large Language Models with GPT4All
By
–
Get a Taste of LLMs from GPT4All! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding #100DaysofCode https://
geni.us/Get-LLMs-GPT4A
LL
… -
LLMs Cannot Replace Quality Writing and Persuasion
By
–
People who think LLMs can replace writing are people who don't appreciate good writing (but would if it were removed). Crappy content marketing is not what we should hope to emulate. Sure, a machine can do that.But writing that deeply informs and persuades? That's art not science
-
Building LLM Applications for Production Environments
By
–
Building LLM applications for production https://
bit.ly/3WmiCfh #AI #MachineLearning #DeepLearning #LLMs #DataScience -
H2O Meetup: Create and Fine-Tune Your Own LLMs in Dallas
By
–
Curious about #OpenSource #LLMs and #GPT? Join @h2oai for a #MeetUp on May 24, 6:30-8:30 PM @SMU in Dallas! Make and fine-tune your own LLMs using Open Assistant datasets. Register: https://
h2o.ai/events/live/ma
ke-your-own-gpt-dallas/
… #h2oGPT #GenerativeAI #MachineLearning #H2OLLMStudio #DemocratizeAI -
PaLM’s Multilingual Capabilities: Translation Pairs Across 44 Languages
By
–
10/ Searching for Needles in a Haystack – shows that PaLM is exposed to over 30 million translation pairs across at least 44 languages; shows that incidental bilingualism connects to the translation capabilities of PaLM.
-
CodeT5+ Achieves State-of-the-Art Code Understanding and Generation
By
–
8/ CodeT5+ – supports a wide range of code understanding and generation tasks and different training methods to improve efficacy and computing efficiency; achieves SoTA on tasks like code completion, math programming, and text-to-code retrieval tasks.
-
Symbol Tuning Boosts Language Models In-Context Learning Performance
By
–
9/ Symbol Tuning – an approach to finetune LMs on in-context input-label pairs where natural language labels are replaced by arbitrary symbols; boosts performance on unseen in-context learning tasks and algorithmic reasoning tasks.