Miguel Guerrero's picture

Miguel Guerrero

apol

·

http://miguelguerrero.me/

AI & ML interests

nlp, avatars, gans, time series, alzheimer, education

Recent Activity

liked a dataset 4 days ago

HuggingFaceTB/stack-edu

liked a model 8 days ago

open-r1/OlympicCoder-7B

View all activity

Organizations

apol's activity

upvoted 2 collections 8 days ago

Foundation Models for Vision 🧩

Foundation models for computer vision. • 24 items • Updated Mar 11, 2024 • 20

Vision Language Leaderboards

This collection has all the vision language leaderboards. • 7 items • Updated Aug 24, 2024 • 19

upvoted a collection 21 days ago

Leaderboards and benchmarks ✨

Cool leaderboard spaces collection for models across modalities! Text, vision, audio, ... • 91 items • Updated 25 days ago • 99

upvoted a paper 24 days ago

Towards an AI co-scientist

Paper • 2502.18864 • Published 27 days ago • 44

upvoted an article 28 days ago

Article

FastRTC: The Real-Time Communication Library for Python

29 days ago

• 147

upvoted a paper about 2 months ago

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Paper • 2501.05366 • Published Jan 9 • 98

upvoted an article about 2 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.19k

upvoted a paper about 2 months ago

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

Paper • 2502.01061 • Published Feb 3 • 197

upvoted an article about 2 months ago

Article

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

Jan 28

• 822

upvoted a collection about 2 months ago

Qwen2.5-1M

The long-context version of Qwen2.5, supporting 1M-token context lengths • 3 items • Updated 27 days ago • 108

upvoted 2 collections 2 months 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 about 1 hour ago • 211

Dolphin 3.0

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model. • 9 items • Updated Feb 7 • 113

upvoted 4 collections 3 months ago

Deepseek V3 (All Versions)

Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions. • 5 items • Updated about 1 hour ago • 33

Cosmos

The collection of Cosmos models • 31 items • Updated 7 days ago • 276

Smol but mighty

A collection of smoll but mighty models • 10 items • Updated Jan 22 • 4

DeepSeek-V3

4 items • Updated about 7 hours ago • 210