Jay Shin
jshin49
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
Trillion 7B Technical Report
liked
a model
3 days ago
trillionlabs/Trillion-LLaVA-7B
new activity
about 1 month ago
trillionlabs/Trillion-7B-preview:MT-bench scores are awkwardly low for EXAONE-3.5-7.8B-Instruct.
Organizations
Collections
7
-
Pre-training Small Base LMs with Fewer Tokens
Paper • 2404.08634 • Published • 36 -
Ziya2: Data-centric Learning is All LLMs Need
Paper • 2311.03301 • Published • 20 -
How to Train Data-Efficient LLMs
Paper • 2402.09668 • Published • 43 -
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Paper • 2404.06395 • Published • 23
models
None public yet
datasets
None public yet