Ready to test these new features?
Add your keys, start generating trials, and unlock the full potential of the playground.
18.12.2024 21:51 β π 7 π 0 π¬ 0 π 0
While trials work seamlessly with most models, some like o1 currently donβt support choices.
Weβre actively working to enable this in the future. Stay tuned!
18.12.2024 21:51 β π 7 π 0 π¬ 1 π 0
The magic doesnβt stop there.
Once you pick the best output, you can continue your exploration as if that output is how the model wouldβve answered.
See how the conversation unfolds from your chosen result!
18.12.2024 21:51 β π 6 π 0 π¬ 1 π 0
Trials really shines when temperature settings are turned up. π₯
Explore the modelβs creativity by generating multiple outputs at once and comparing the diverse responsesβall at a glance.
18.12.2024 21:51 β π 0 π 0 π¬ 1 π 0
Choosing the best model output often means iteration.
Playground trials will save you time by letting you compare multiple results side-by-side before committing to one. π΅
18.12.2024 21:51 β π 0 π 0 π¬ 1 π 0
Weβve added trials to the playground!
Now, you can generate multiple outputs for the same input.
Simply bump up the βNumber of Trialsβ in the settings sidebar to see various options before continuing your work.
18.12.2024 21:51 β π 0 π 0 π¬ 1 π 0
π οΈ New tools in the W&B playground are here!
Amazon Nova models & xAI's Grok beta LLM are now available.
Add your API keys in team settings to start exploring these powerful models today. π
Hereβs whatβs new: π
18.12.2024 21:51 β π 4 π 0 π¬ 1 π 0
language model pretraining @ai2.bsky.social, co-lead of data research w/ @soldaini.net, statistics @uw, open science, tabletop, seattle, he/him,π§ kyleclo.com
I like tokens! Lead for OLMo data at @ai2.bsky.social (Dolma π) w @kylelo.bsky.social. Open source is fun π€βοΈππ³οΈβπ Opinions are sampled from my own stochastic parrot
more at https://soldaini.net
Asst Prof @uwischool.bsky.social; #NLP #healthinformatics #accessibility #scholcomm
π΄ποΈπβοΈβ·οΈπ§Άβ«οΈβͺοΈππΈin Seattle; llwang.net; she/her
asst prof of computer science at cu boulder
nlp, cultural analytics, narratives, communities
books, bikes, games, art
https://maria-antoniak.github.io
Postdoc @ai2.bsky.social & @uwnlp.bsky.social
I (try to) do NLP research. Antipodean abroad.
currently doing PhD @uwcse,
prev @usyd @ai2
π¦πΊπ¨π¦π¬π§
ivison.id.au
Breakthrough AI to solve the world's biggest problems.
βΊ Join us: http://allenai.org/careers
βΊ Get our newsletter: https://share.hsforms.com/1uJkWs5aDRHWhiky3aHooIg3ioxm
Tenure-track faculty at the Max Planck Institute for Software Systems
Previously postdoc at UW and AI2, working on Natural Language Processing
Recruiting PhD students!
π https://lasharavichander.github.io/
NLP research - PhD student at UW
Associate professor of social computing at UW CSE, leading @socialfutureslab.bsky.social
social.cs.washington.edu
Postdoc at UW NLP ποΈ. #NLProc, computational social science, cultural analytics, responsible AI. she/her. Previously at Berkeley, Ai2, MSR, Stanford. Incoming assistant prof at Wisconsin CS. lucy3.github.io
Assistant Professor of CS, University of Southern California. NLP / ML.
Asst prof @ University of Utah Β· NLP Β· she/her ππ·
AI, RL, NLP, Games Asst Prof at UCSD
Research Scientist at Nvidia
Lab: http://pearls.ucsd.edu
Personal: prithvirajva.com
assistant professor, @ltiatcmu.bsky.social. machine learning: LLMs and climate. π³οΈβππ³οΈββ§οΈ they/them/dad (2 dogs).
pro-AI, anti-capitalist, anti-fascist.
Website: strubell.github.io
Asst Prof @UMD Info College. NLP, computational social science, political communication, linguistics. Past: Data Science Postdoc @UChicago, Info PhD @UMich, CS + Lx @Stanford. Interests: cats, Yiddish, talking to my cats in Yiddish.
Researcher & entrepreneur | Co-founder @cosmik.network | Building @semble.so | collective sensemaking | https://ronentk.me/ | Ecosystem building @atproto.science | Prev- Open Science Fellow @asterainstitute.bsky.social
Senior Lecturer at @CseHuji. #NLPROC
schwartz-lab-huji.github.io
