AthenaAgent
5 posts
AthenaAgent
@AthenaAgentRL
Post training production-grade AI agents
San Francisco, CA Katılım Mayıs 2024
1 Takip Edilen689 Takipçiler
AthenaAgent retweetledi
The Aryabhatta 1.0 paper drop happened!
Finally! Sorry for the delay!
This paper talks about composition of our training datasets, some details about our training methodologies and few interesting tidbits about how we did effective exploration with RLVR.
Do checkout and dm me / @RitvikRastogi19 for any questions.
Paper link 👇
Sachin@sachdh
Excited to share Aryabhatta 1.0, our leading model that scores 90.2% on JEE Mains, outperforming frontier models like o4 mini and Gemini Flash 2.5 Trained by us at @AthenaAgentRL , in collaboration with @physics__wallah, using custom RLVR training on 130K+ curated JEE problems 7B parameters and 4K context is all you need to crack JEE Also, you don’t need to blindly follow GRPO. Custom objective functions make a huge difference Details below 👇
English
AthenaAgent retweetledi
a very good (and a rare one in India) to work on tough problems and with @sachdh, apply guys!
Sachin@sachdh
want to prepare for the same skills? want to train the models to solve hard tasks? want to join the early, chaotic but extremely ambitious pirate ship? we are hiring and DMs are open. if you dont care about leetcode and trad job routes; but just want to take on ambitious projects, we have a home for you. we aspire to build frontier artificial narrow intelligence lab. if you care about data quality, can write custom pytorch code, enjoy reading logs; then ping me with - your favorite deep learning paper / blog - the weird project which you are proud of - given unlimited resources, what problem do you want to solve
English
AthenaAgent retweetledi
want to prepare for the same skills?
want to train the models to solve hard tasks?
want to join the early, chaotic but extremely ambitious pirate ship?
we are hiring and DMs are open.
if you dont care about leetcode and trad job routes; but just want to take on ambitious projects, we have a home for you.
we aspire to build frontier artificial narrow intelligence lab.
if you care about data quality, can write custom pytorch code, enjoy reading logs; then ping me with
- your favorite deep learning paper / blog
- the weird project which you are proud of
- given unlimited resources, what problem do you want to solve
TDM (e/λ) (L8 vibe coder 💫)@cto_junior
Whatever gold rush is happening in valley, will happen in Bangalore in max next 2 years So if you're feeling lost seeing those large comps, just prepare for the same skills Time will reward you well (somewhat PPP adjusted)
English
AthenaAgent retweetledi
Excited to share Aryabhatta 1.0, our leading model that scores 90.2% on JEE Mains, outperforming frontier models like o4 mini and Gemini Flash 2.5
Trained by us at @AthenaAgentRL , in collaboration with @physics__wallah, using custom RLVR training on 130K+ curated JEE problems
7B parameters and 4K context is all you need to crack JEE
Also, you don’t need to blindly follow GRPO. Custom objective functions make a huge difference
Details below 👇
English