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
…
@jeande_d
-
Code Interpreter Review by Ethan Mollick: Experiments and Analysis
By
–
-
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
-
SOTA Multimodal Models Without ViT Vision Encoders
By
–
I was actually thinking lately if there is any SOTA multimodal that is not using ViT as vision encoder.
-
nanoT5: Fast T5 Model Pretraining and Finetuning on Single GPU
By
–
nanoT5 – Fast & Simple repository for pretraining and finetuning T5-style models A code repository for pretraining and finetuning T5 LLMs(one of the earliest encoder-decoder models) under a limited budget. – Achieves 40.7 RougeL in 16 hrs on a single GPU(original T5 on Hugging
-
Exciting Long-Form Technical Content on AI Fundamentals and Research
By
–
Something that I am super excited about is long-form technical contents grounded on fundamentals and recent advances in AI research. More on this soon and other updates 😀
-
Stage Review of Instruction Tuning: LLaMA Models and Future Challenges
By
–
A Stage Review of Instruction Tuning A really nice article about instruction tuned models based on LLaMA. Discusses recent instruction tuned models and the next challenges of instruction tuning. (instruction tuning -> instruction fine-tuning) https://
yaofu.notion.site/June-2023-A-St
age-Review-of-Instruction-Tuning-f59dbfc36e2d4e12a33443bd6b2012c2
… -
MPT-7B/30B: Analysis of MosaicML’s Open-Source LLM Benefits
By
–
Detailed analysis of the beneficial traits of MPT-7B/30B by MosaicML in open-source foundational large language models (LLMs).
-
Clarifying terminology: LMs, LLMs, and MLLMs explained
By
–
The terms are confusing, I know. LMs are language models. LLMs are large LMs. MLLMs are multimodal LLMs where LLMs are treated as the "prime generalization engine". People using MLLMs in papers should probably say LMM(large multimodals) but I guess they append LLMs to take
-
Survey on Multimodal Large Language Models and Instruction Tuning
By
–
A Survey on Multimodal Large Language Models Large multimodals are likely going to be one of the next big things in AI research. This is a great survey on multimodal large language models(MLLM). Talks about topics like multimodal instruction tuning, multimodal in-context
-
Large Action Models: LLM Extension for Independent Task Accomplishment
By
–
This is a great article on Large Action Models(LAM), a possible extension of LLMs that can do much more than what they do currently. Large Action Models as "agents that accomplish tasks and make decisions independently". https://
blog.salesforceairesearch.com/large-action-m
odels/
…