LLMS

→ View original post on X — @alexandr_wang

Coders Using AI as 10x Stack Overflow with RLHF

By

@alexandr_wang

–

09 February 2023 20h29

ok I will now admit that coders are using it everyday as 10x stackoverflow good thing they did all that coding RLHF!

Predicting Large Model Performance Across Unseen Tasks

By

–

09 February 2023 18h56

(3 cont.) Can you predict the performance of one model from another?
Can you predict the performance of a 128B model on an unseen task, given models up to some smaller threshold size and some performances of 128B models on other tasks?

Hope for Better Open-Source Large Language Models

By

–

09 February 2023 18h56

Finally, with models like OPT and BLOOM at 175B params, I'm hopeful that better open-source models will be soon be trained, given the pace of innovation in the space.

BIG-Bench metrics deserve deeper analysis and study

By

–

09 February 2023 18h56

(3) Even just looking at BIG-Bench metrics is quite understudied IMO. There are hundreds of tasks in BIG-Bench, and each task has dozens of models evaluated, each with many evaluation metrics. There are task logs for some models. This raises natural questions:

Flan-T5 Public Release with Instruction Tuning Data Ablation

By

–

09 February 2023 18h56

(2 cont.) Flan-t5 is publicly available along with the dataset (thanks to @ShayneRedford
), so you can even ablate parts of the instruction tuning data to see what unlocks performance.

Unlocking emergent abilities in smaller language models like Flan-T5

By

–

09 February 2023 18h56

(2) One key question of emergence is how to unlock such abilities at smaller scales, and I don't think there has been much work on flan-T5, which often beats PaLM 62B as shown in this paper: https://
arxiv.org/abs/2210.11416

→ View original post on X — @dotcsv

Open Assistant: Community-Driven Open Source ChatGPT Alternative

By

@dotcsv

–

09 February 2023 17h33

NEW VIDEO! Can you imagine an Open Source ChatGPT? Created by and for the community, available to create, research, and use freely. That's the idea behind Open Assistant! And we need your help to make it speak good SPANISH well https://
youtu.be/XYT1TxINbuM
—

→ View original post on X — @goodside

Bing’s real star is unnamed next-gen OpenAI model, not Prometheus

By

@goodside

–

09 February 2023 17h18

I suspect the real star of Bing Search is the strategically unnamed "next-generation OpenAI model." Prometheus seems to be the prompt + search augmentation. The underlying model is tuned to be a white-label ChatGPT for search applications generically.