LlamaIndex is something i see around so much but never figured out what it does. i've always considered it noise. A general rule of thumb is anyone serious about LLMs should not touch either of these.
LLMS
-
ChatGPT Transformed Business: Marketing AI Institute’s Game-Changing Innovation
By
–
I feel this in my soul. For Marketing AI Institute (
@MktgAi
), founded in 2016, the new innovation that changed everything was ChatGPT. Woke the world up the potential of AI to transform business (and society). -
Stability AI Advocates for Open Models in AI Senate Oversight
By
–
Advocating for Open Models in AI Oversight: Stability AI's Letter to the United States Senate — Stability AI https://
bit.ly/42TPdvv #AI #MachineLearning #DeepLearning #LLMs #DataScience -
OpenAI and Microsoft sued for $3 billion over alleged internet data scraping
By
–
OpenAI and Microsoft are being sued in California for scraping "300 billion words from the internet." All 16 plaintiffs are anonymous, and seeking $3 billion in damages because ChatGPT may or may not have been trained on their data. Court filing: https://
storage.courtlistener.com/recap/gov.usco
urts.cand.414754/gov.uscourts.cand.414754.1.0.pdf
… -
Code Interpreter Review by Ethan Mollick: Experiments and Analysis
By
–
Here is a nice review about Code Interpreter by @emollick
. Well written and lots of experiments there! https://
oneusefulthing.org/p/what-ai-can-
do-with-a-toolbox-getting
… -
Code Interpreter by OpenAI: A Game-Changing AI Assistant
By
–
Code Interpreter by OpenAI is truly a game changer. It's an analyst/assistant on your fingertip, who have general knowledge about the world(such as mathematics, stats, economics, etc…), who can answer your questions with beautiful visualizations, who can code, etc… Like many
-
Roberta-Large and Decoder-Style LLMs Comparison
By
–
I would consider Roberta-Large (see above) an LLM. But you are also welcome to swap that with decoder-style LLMs. I have a BLOOM (GPT-3 equivalent) example here:
-
Positional Embeddings and Learned Query-Key Weights in Transformers
By
–
That's true, but you still have positional embeddings, and Q and K weights that are learned
-
Fine-tuning RoBERTa for Sentiment Classification to 95% Accuracy
By
–
Then, you can boost that performance (on the same movie review sentiment classification dataset) to ~95% finetuning model = AutoModelForSequenceClassification.from_pretrained( "siebert/sentiment-roberta-large-english", num_labels=2)
-
Ditching Word2Vec for Superior LLM Embeddings in Classification
By
–
I would ditch Word2Vec; the embeddings learned by LLMs are much better. For sentiment classification, you can start with DistilBERT as a base model and tune a few layers (see https://
magazine.sebastianraschka.com/p/finetuning-l
arge-language-models
…) 1/2