Hints of things to come via this research paper of
#LargeLanguageModel’s #LLM’s in Finance Will S&OP & Integrated Business Planning be next?
MT @KirkDBorne cc @PawlowskiMario @Nicochan33 @pascal_bornet @mvollmer1 @BlueYonder @alvinfoo @EvanKirstel https://
ar5iv.labs.arxiv.org/html/2310.17784
LLMS
-
LLMs in Finance: S&OP and Integrated Business Planning Applications
By
–
-
GPT-4 Existence Confirmed Since Summer 2022
By
–
Gary anda despistadillo, pero desde hace un año Satya confirmó que GPT-4 existía (y se lo enseñaron) desde verano del 22.
-
Exporting Model Weights for Faster Evaluation Infrastructure
By
–
Instead of building them out inside llm.c it might be faster to export the model weights into "common infra" and run evals with that. I don't have time to get around to it right away but made an Issue a few days ago for someone to potentially take a look.
-
Pretraining Datasets and Evaluation Metrics for Multilingual Models
By
–
Yes, definitely, my last tweet few seconds ago is also on this point. And many pretraining datasets also care about e.g. multilignual, code, math, etc., so it's not clear how those evals would be affected.
-
GPT-3 Training Surpasses Expected Performance on FineWeb Dataset
By
–
Example here is the llm.c GPT-3 (124M) training on FineWeb (figure cropped at 250B tokens), we seem to surpass GPT-3 HellaSwag (green line) at ~150B tokens, per paper expected this to be at 300B tokens. Will re-run with FineWeb-Edu. I do want to be a bit careful on conclusions
-
Fine-tune LLMs for enterprise apps with MLflow
By
–
Register for trainings at #DataAISummit! In the LLM-focused track, learn how to: Prepare data for supervised fine-tuning Fine-tune downstream LLMs within enterprise apps Integrate a fine-tuning pipeline with MLflow + #UnityCatalog Join us: https://
dbricks.co/3R9GvVY -
llm.c Outperforming GPT-2/3 with Fewer Training Tokens
By
–
In llm.c pretraining we were already mildly perplexed why seem to be outperforming GPT-2 & 3 (124M) training on just 10B tokens instead of something closer to 100-300B, per the original papers. I suspect a good chunk of it may be just the dataset quality, so I'm eager to retrain
-
FineWeb-Edu: High-Quality LLM Dataset Filtering for Better Learning
By
–
Awesome and highly useful: FineWeb-Edu High quality LLM dataset filtering the original 15 trillion FineWeb tokens to 1.3 trillion of the highest (educational) quality, as judged by a Llama 3 70B. +A highly detailed paper. Turns out that LLMs learn a lot better and faster
-
Language Translation Using LSTM for NLP Sequential Data
By
–
Language Translation Using LSTM: Introduction In natural language processing (NLP), it is important to understand and effectively process sequential data.… https://
analyticsvidhya.com/blog/2024/04/l
anguage-translation-using-lstm/?utm_source=dlvr.it&utm_medium=twitter
… #DataAnalytics #DataScience #DataDriven #BusinessIntelligence #IoT #CTO #ITDirector #Blockchain -
Awesome LLM Apps with RAG and AI Agents Repository
By
–
Thank you for sharing. Find all the awesome LLM apps with RAG and AI agents in this opensource repository.