Mike Ravkine PRO

mike-ravkine's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 1 month ago

The End of Manual Decoding: Towards Truly End-to-End Language Models

Paper • 2510.26697 • Published Oct 30 • 115

upvoted 3 articles about 1 month ago

view article

Article

Vision Tokens vs Text Tokens: Understanding the 10× Compression

• 

Oct 22

•

6

view article

Article

All LLMs Write Great Code, But Some Make (A Lot) Fewer Mistakes

• 

Sep 12, 2024

•

5

view article

Article

Hall of Multimodal OCR VLMs and Demonstrations

• 

Oct 31

•

5

upvoted a collection about 2 months ago

aquif-4

Collection

aquif-4-Exp is the first hybrid attention model from aquif, built on a strong architecture with 256 experts. • 2 items • Updated 3 days ago • 3

upvoted a paper about 2 months ago

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs

Paper • 2510.05069 • Published Oct 6 • 12

upvoted a paper 3 months ago

Symbolic Graphics Programming with Large Language Models

Paper • 2509.05208 • Published Sep 5 • 46

upvoted an article 4 months ago

view article

Article

Supercharge Edge AI With High‑Accuracy Reasoning Using NVIDIA Nemotron Nano 2 9B

• 

Aug 18

•

31

upvoted a collection 11 months ago

Lumimaid 0.2

Collection

4 items • Updated Jul 26, 2024 • 20

upvoted a paper 12 months ago

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

Paper • 2412.11919 • Published Dec 16, 2024 • 36

upvoted a paper about 1 year ago

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

Paper • 2410.10139 • Published Oct 14, 2024 • 51

upvoted a collection about 1 year ago

My most recent datasets

Collection

6 items • Updated Oct 8, 2024 • 6

upvoted an article about 1 year ago

view article

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

• 
• 
• +4

Sep 18, 2024

•

272

upvoted a collection about 1 year ago

Qwen2.5-Coder

Collection

Code-specific model series based on Qwen2.5 • 40 items • Updated Jul 21 • 348

upvoted a paper about 1 year ago

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Paper • 2409.01704 • Published Sep 3, 2024 • 83

upvoted 2 collections over 1 year ago

Multimodal RAG

Collection

10 items • Updated Sep 5, 2024 • 30

Hermes 3

Collection

The Hermes 3 Series of Models • 11 items • Updated Sep 8 • 132

upvoted a paper over 1 year ago

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

Paper • 2407.14057 • Published Jul 19, 2024 • 46

upvoted a collection over 1 year ago

Personal Favorites

Collection

Recommended models I use often or like for any reason. I recommend reading their cards for more details. • 10 items • Updated Dec 24, 2024 • 92

upvoted a collection almost 2 years ago

Quyen

Collection

State-of-the-arts General LLMs - based on Qwen1.5 • 26 items • Updated Feb 13, 2024 • 12