Mayank Bhaskar's picture

Mayank Bhaskar

cataluna84

·

AI & ML interests

Research interest includes anything that moves or in processing things that are on the audible spectrum and has recently been seduced by RL Theory, GNNs, Transformers & applications of them in solving self-driving autonomous systems including vehicles, drones, and robots.

Recent Activity

upvoted a collection about 7 hours ago

🧪 FineWeb v1 data experiments

upvoted a collection about 7 hours ago

📀 Dataset comparison models

liked a Space about 7 hours ago

HuggingFaceFW/discussion

View all activity

Organizations

cataluna84's activity

upvoted 3 collections about 7 hours ago

🧪 FineWeb v1 data experiments

Ablation models trained for our data experiments. • 22 items • Updated Jun 12, 2024 • 5

📀 Dataset comparison models

1.8B models trained on 350BT to compare different pretraining datasets • 8 items • Updated Jun 12, 2024 • 37

🥂 FineWeb2

3 items • Updated Dec 8, 2024 • 13

upvoted an article 1 day ago

Article

Open-source DeepResearch – Freeing our search agents

3 days ago

• 626

upvoted an article 6 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

10 days ago

• 646

upvoted 2 papers 8 days ago

Baichuan-Omni-1.5 Technical Report

Paper • 2501.15368 • Published 11 days ago • 53

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published 11 days ago • 54

upvoted a collection 9 days ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 3 items • Updated 10 days ago • 320

upvoted a paper 14 days ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published 15 days ago • 298

upvoted a collection 15 days ago

DeepSeek-R1

8 items • Updated 17 days ago • 416

upvoted an article 15 days ago

Article

ZebraLogic: Benchmarking the Logical Reasoning Ability of Language Models

By

•

Jul 27, 2024

• 30

upvoted 2 collections 16 days ago

DeepSeek R1 (All Versions)

DeepSeek R1 - the most powerful reasoning open-source model - available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 29 items • Updated 1 day ago • 149

Deepseek V3 (All Versions)

Deepseek V3 - available in bf16, original, and GGUF formats, with support for 2, 3, 4, 5, 6 and 8-bit quantized versions. • 3 items • Updated 2 days ago • 29

upvoted a paper 17 days ago

Simplified State Space Layers for Sequence Modeling

Paper • 2208.04933 • Published Aug 9, 2022 • 1

upvoted an article 17 days ago

Article

Introduction to State Space Models (SSM)

By

•

Jul 19, 2024

• 108

upvoted a paper 17 days ago

Efficiently Modeling Long Sequences with Structured State Spaces

Paper • 2111.00396 • Published Oct 31, 2021 • 2

upvoted 2 papers 19 days ago

Transformer^2: Self-adaptive LLMs

Paper • 2501.06252 • Published 29 days ago • 53

Tensor Product Attention Is All You Need

Paper • 2501.06425 • Published 26 days ago • 80

upvoted 2 collections 20 days ago

Meta's Llama 3.3 models & evals

2 items • Updated Dec 13, 2024 • 38

SQFT

SQFT Models (SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models) • 56 items • Updated Nov 14, 2024 • 2