Max Glushko

Pelmeshek

Pelmeshek1706

AI & ML interests

NLP, LLM, SLM

Recent Activity

liked a model 2 days ago

google/gemma-3-27b-it

upvoted a collection 6 days ago

Gemma 3 Release

upvoted a paper 25 days ago

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

View all activity

Organizations

None yet

Pelmeshek's activity

liked a model 2 days ago

google/gemma-3-27b-it

Image-Text-to-Text • Updated 6 days ago • 241k • • 751

upvoted a collection 6 days ago

Gemma 3 Release

Collection

9 items • Updated 4 days ago • 263

upvoted a paper 25 days ago

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

Paper • 2502.14499 • Published 26 days ago • 181

liked a Space 25 days ago

2.29k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

liked a model 25 days ago

perplexity-ai/r1-1776

Text Generation • Updated 20 days ago • 60.3k • • 2.15k

upvoted an article 25 days ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.17k

liked 3 models about 1 month ago

reacted to Jaward's post with 👀 3 months ago

Post

3099

nanoBLT: Simplified lightweight implementation of a character-level Byte Latent Transformer model (under 500 lines of code). The model is 2x4x2 (n_layers_encoder, n_layers_latent, n_layers_decoder) layer deep trained on ~1M bytes of tiny Shakespeare with a patch size of 4.

Code: https://github.com/Jaykef/ai-algorithms/blob/main/byte_latent_transformer.ipynb