Maithra Raghu | Does One Large Model Rule Them All? https://
bit.ly/3Iq5i3X #AI #MachineLearning #DeepLearning #LLMs #DataScience
LLMS
-
Does One Large Model Rule Them All? – Maithra Raghu
By
–
-
SlimPajama Tools Released for Building AI Models
By
–
Here are the tools we created to build SlimPajama. Have fun! x.com/dmsobol/status…
-
SlimPajama Tools Released for Open Source AI
By
–
Here are the tools we created to build SlimPajama. Have fun!
-
Integrate with Hugging Face Transformers and Text Generation Inference
By
–
Nice! You should be integrate it with hf/transformers or https://
github.com/huggingface/te
xt-generation-inference
… -
AI Chat Platform for End-to-End ML and LLM Operations
By
–
Use our AI chat to program our end-to-end ML and LLM Ops platform – execute code – draw plots – analyze dataset – transform data – fine-tune LLMs You talk to the bot, and the AI bot builds ML models and deploys them in production.
-
Perplexity advances answer engines with personalization and memory
By
–
The next phase of answer engines and copilots is to be able to remember you, what you like and prefer, personalize your experience and save you from the drudgery of repetitive prompting. We’re excited to take the first step towards building a unique https://t.co/FJJkocQcJf… https://t.co/XOJ97d7Rua
— Aravind Srinivas (@AravSrinivas) 9 juin 2023The next phase of answer engines and copilots is to be able to remember you, what you like and prefer, personalize your experience and save you from the drudgery of repetitive prompting. We’re excited to take the first step towards building a unique http://
Perplexity.ai -
Efficient LLM Fine-tuning with LoRA Tutorial on Keras
By
–
Awesome new tutorial on http://
keras.io: how to use LoRA to perform very efficient fine-tuning of LLMs. -
RedPajama Project Launches with OpenTensor and Together Support
By
–
We’d like to thank our partner @opentensor for supporting this project. And credit goes to @togethercompute and the entire team that created the RedPajama dataset! We can’t wait to see what you’ll build. Join our Discord and let us know your feedback: https://
discord.com/channels/10859
60591052644463/1085960592050896937
… -
SlimPajama: 50% Smaller, Twice Faster LLM Training Dataset
By
–
SlimPajama cleans and deduplicates RedPajama-1T, reducing the total token count and file size by 50%. It's half the size and trains twice as fast! It’s the highest quality dataset when training to 600B tokens and when upsampled performs equal or better than RedPajama.
-
SlimPajama: High-Quality Dataset Reduces Duplicates Training
By
–
RedPajama-1T is the largest open dataset today but contains a large percentage of duplicates, making a full training run costly and inefficient. Like the Falcon team, we found data quality is just as important as quantity – which led to SlimPajama.