Great article! >> @Pluto7_Services
, Google Cloud, and @SAP are leading the data revolution: https://
pluto7.com/2023/05/16/lea
ding-the-data-revolution/
…
=====
#SAPSapphire #AI #MachineLearning #BigData #DataScience #GenerativeAI #LLMs #Chatbot #NLProc #DataStrategy
LLMS
-
Pluto7, Google Cloud, and SAP Lead Data Revolution
By
–
-
LangChain Debug Mode Enables Full Execution Traces Logging
By
–
Debug Mode `import langchain; langchain.debug=True` A much requested feature! You can now get full traces printed out to the console. Along with token usage, LLM info, etc. Should be super handy for debugging complex chains and agents
-
HTML to Markdown Conversion Tool for LLM Document Processing
By
–
HTML 2 Markdown There's lot of interesting data in websites, but raw html is often too messy/big to pass to LLMs With http://
2markdown.com by @andinfinity_eu you can just convert that to markdown! Now a @langchain document loader Docs: https://
python.langchain.com/en/latest/modu
les/indexes/document_loaders/examples/tomarkdown.html
… -
NVIDIA ServiceNow Partnership Develops Custom Enterprise LLMs
By
–
We are partnering with @ServiceNow to develop custom large language models built on the ServiceNow platform with NVIDIA #AI software and DGX infrastructure to bring intelligent workflow automation to enterprises. Learn more: https://
nvda.ws/458XeOI #IT #GenAI -
OpenAI’s embedding model ada-002 faces Hong Kong University competition
By
–
It's also worth mentioning that OpenAI has a lot to lose here. Its foundation models are the standard right now (like 90% of the people I talk to use GPT-4). But its text embedding model, ada-002, isn't actually the best one available. That one comes out of Hong Kong University.
-
ChatGPT Sparked AI Development Shift Toward Smaller Models
By
–
OpenAI triggered a Cambrian explosion in AI development with the release of ChatGPT. That was six months ago, and already developer efforts (especially in OSS) have shifted to focus on squeezing more performance out of smaller models. And even that's getting old!
-
Comparing Language Models: Sparse, Dense, and Parameter Scaling Issues
By
–
so many problems i don't know where to begin.
– yea put sparse and dense models in the same plot with the # params. good job – i'm sure you know the size of palm-2 and gpt-4. – fwiw, t5 is still one of the best LM models out there. it started way earlier than 2021. – -
Senators Question Constitutional AI versus RLHF Technology
By
–
wild times hearing senators asking about constitutional ai vs. rlhf
-
Webinar on Hallucinations in Document Question Answering
By
–
Webinar on hallucinations in document question answering tasks starting now Hopefully none of the panelists (
@nickscamara_ @awadallah @sfgunslinger @deepset_ai ) hallucinate any answers themselves! -
OpenAI CEO Claims Era of Giant AI Models Ending
By
–
OpenAI’s CEO Says the Age of Giant AI Models Is Already Over https://
bit.ly/3KU77Xn #AI #DeepLearning #MachienLearning #DataScience #GenAI