QED-Nano: Teaching a Tiny Model to Prove Hard Theorems
📝
74
Who needs 1T parameters? Olympiad proofs with a 4B model
Arun Prakash
arun-AiBharat
AI & ML interests
LLMs, OCR
Recent Activity
liked a Space 2 months ago
lm-provers/qed-nano-blogpost upvoted an article 3 months ago
Gotchas in Tokenizer Behavior Every Developer Should Know liked a model 4 months ago
google/translategemma-12b-itOrganizations
liked a
Space 2 months ago
upvoted an article 3 months ago
Article
Gotchas in Tokenizer Behavior Every Developer Should Know
qgallouedec
• • 72 liked a
model 4 months ago
liked a
Space 7 months ago
upvoted an article 9 months ago
Article
The N Implementation Details of RLHF with PPO
- +1
vwxyzjn, tianlinliu0121, lvwerra
• • 72 upvoted 2
articles 10 months ago
Article
Welcome GPT OSS, the new open-source model family from OpenAI!
- +10
reach-vb, pcuenq, lewtun, clem, Rocketknight1, clefourrier, celinah, Wauplin, marcsun13, pagezyhf, ahadnagy, joaogante
• • 513 Article
Illustrating Reinforcement Learning from Human Feedback (RLHF)
- +2
natolambert, LouisCastricato, lvwerra, Dahoas
• • 413 commented on Mixture of Experts Explained 10 months ago
Here is an illustration that helps you understand the routing process visually. Source 
A simple visualization of moe block
#524 opened 10 months ago
by arun-AiBharat
upvoted an article 10 months ago
Article
Mixture of Experts Explained
- +4
osanseviero, lewtun, philschmid, smangrul, ybelkada, pcuenq
• • 1.13k liked a
Space 10 months ago
upvoted an article 10 months ago
Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf
• • 776 upvoted 3
articles about 1 year ago
Article
Let's talk about LLM evaluation
clefourrier
• • 209 Article
Open LLM Leaderboard: DROP deep dive
- +3
clefourrier, cabreraalex, stellaathena, SaylorTwift, thomwolf
• • 11 Article
What's going on with the Open LLM Leaderboard?
- +2
clefourrier, SaylorTwift, slippylolo, thomwolf
• • 51 liked a
dataset about 1 year ago
updated 2
datasets over 1 year ago
liked a
dataset over 1 year ago
version-2-40k-steps
1
#2 opened over 1 year ago
by arun-AiBharat