upcarta
Sign In
Sign Up
Explore
Search
Natural language processing
Follow
4
Followers
Most Recommended
Recent Content
Most Recommended
Paper
Tweet
Article
Video
Book
Podcast episode
Tweet
Mar 30, 2023
There are several NLP tasks. Here are the most common ones, with example demos🔥: --A Thread-- 🧵
by
mwiti
Post
Add to Collection
Mark as Completed
Tweet
Oct 23, 2023
So my👇 thread about our papers investigating the verification and self-critiquing inabilities of GPT4 has apparently resonated with a lot of folks. Here is a quick response to several issues raised (either in replies or other quote-tweet threads). [
by
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
Post
Add to Collection
Mark as Completed
Tweet
Jul 1, 2023
People always ask if prompt engineering is going to go away over time. My short answer is "no". But, a more nuanced answer is that the goal of prompt engineering has evolved over time: from nudging a finnicky language model to do an "easy" task (2020
by
Jason Wei
Post
Add to Collection
Mark as Completed
Tweet
May 11, 2023
👨💻 thoughts on the epistemology of search, and what is implied by the Great LLM Shift: the old school “ten blue links” made sense in an era where avg quality of the web’s long tail was pretty good, and the human curation on individual websites did a
by
Tim Hwang
Post
Add to Collection
Mark as Completed
Tweet
May 9, 2023
Training NLP and CV models from scratch is a waste of resources ❌ Instead, apply transfer learning using pre-trained models 🤖 Here's how transfer learning works in 6 steps 🪜 --A Thread-- 🧵
by
mwiti
Post
Add to Collection
Mark as Completed
Tweet
May 7, 2023
Is it possible to acknowledge that LLMs like ChatGPT are in some sense 'powerful' without playing into the hands of the AGI cultists and the big tech firms boosting them? I think so, and I'd even say that properly confronting them actually requires i
by
Reuben Binns
Post
Add to Collection
Mark as Completed
Tweet
May 5, 2023
MPT is here! Check out our shiny new LLMs, open-source w/commercial license. The base MPT-7B model is 7B params trained on 1T tokens and reaches LLaMA-7B quality. We also created Instruct (commercial), Chat, and (my favorite) StoryWriter-65k+ variant
by
Jonathan Frankle
Post
Add to Collection
Mark as Completed
Tweet
Apr 17, 2023
Okay, @60Minutes is saying that Google's Bard model "spoke in a foreign language it was never trained to know." I looked into what this can mean, and it appears to be a lie. Here's the evidence, curious what others found. 🧵 twitter.com/MelMitchell1/s
by
Margaret Mitchell
Post
Add to Collection
Mark as Completed
Tweet
Apr 3, 2023
There's a lot of folks under the misunderstanding that it's now possible to run a 30B param LLM in <6GB, based on this GitHub discussion. This is not the case. Understanding why gives us a chance to learn a lot of interesting stuff! 🧵 github.com/gge
by
Jeremy Howard
Post
Add to Collection
Mark as Completed
Tweet
Apr 2, 2023
I’m sharing a draft of a slightly-opinionated survey paper I’ve been working on for the last couple of months. It's meant for a broad audience—not just LLM researchers. (🧵) twitter.com/sleepinyourhat/status/1642614846796734464/photo/1
by
Sam Bowman
Post
Add to Collection
Mark as Completed
Tweet
Mar 29, 2023
Are you still deploying DENSE CV and NLP models? You are missing out on the advantages of SPARSE models 🔥. They offer higher throughput and lower latency without negatively affecting accuracy. Checkout out how to deploy sparse models on @huggingfa
by
mwiti
Post
Add to Collection
Mark as Completed
Tweet
Aug 27, 2021
my two cents on why NLP as a field is focusing on the ML-ish / algorithmic / leaderboard-ish aspects (incl., now, LLMs) and not on the underlying language phenomena: it is just so much easier, on so many levels.
by
(((ل()(ل() 'yoav))))👾
Post
Add to Collection
Mark as Completed
Load More
