🔄 In a Training Loop

Alexandros Liapatis

alexliap

P(doom) Rejects the premise

·

AI & ML interests

Generative AI + Traditional ML

Recent Activity

updated a dataset about 7 hours ago

alexliap/greek-cc

liked a Space about 8 hours ago

tardellirs/model-pulse

updated a dataset 1 day ago

alexliap/greek-cc-manifests

View all activity

Organizations

None yet

upvoted a paper 26 days ago

Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts

Paper • 2609.01100 • Published Sep 1 • 1

upvoted a collection about 1 month ago

MobileMoE

a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier • 11 items • Updated Aug 31 • 27

upvoted an article about 1 month ago

Article

Modern LLMs: What the FLIP is an Engram!?

Blackroot

•

Aug 26

• 13

upvoted a collection about 1 month ago

UltraData

Ultra Scale, Ultra Quality, Ultra Coverage • 19 items • Updated 21 days ago • 114

upvoted a collection 4 months ago

ILSP Greek Evaluation Suite

A collection of test sets for evaluating base and chat LLMs (incl. VLMs) on Greek generation and understanding capabilities • 25 items • Updated 11 days ago • 7

upvoted a paper 5 months ago

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

Paper • 2605.22791 • Published May 21 • 31

upvoted a collection 8 months ago

🤏 Smol-Data

Tried and tested mixes for strong pretraining. Inspired by https://huggingface.co/blog/codelion/optimal-dataset-mixing • 14 items • Updated Mar 2 • 21

upvoted a collection 11 months ago

Granite 4.0 Nano Language Models

Ultra-compact language models designed for the edge and on-device deployment. • 17 items • Updated 21 days ago • 103

upvoted a paper about 2 years ago

TimeGPT-1

Paper • 2310.03589 • Published Oct 5, 2023 • 7