Kyle's picture

Kyle PRO

iky1e

·

https://ikyle.me

kylehowells

AI & ML interests

None yet

Recent Activity

liked a model about 18 hours ago

microsoft/VibeVoice-Realtime-0.5B

liked a model 2 days ago

deepseek-ai/DeepSeek-V3.2

liked a model 2 days ago

deepseek-ai/DeepSeek-V3.2-Speciale

View all activity

Organizations

None yet

upvoted an article 2 days ago

Article

We Got Claude to Fine-Tune an Open Source LLM

3 days ago

•

225

upvoted a collection 3 days ago

Parallel Sentences Datasets

These datasets all have "english" and "non_english" columns for numerous datasets. They can be used to make embedding models multilingual. • 14 items • Updated Feb 25 • 20

upvoted a collection 4 days ago

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 4 days ago • 112

upvoted an article 5 days ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

+2

6 days ago

•

223

upvoted a collection 9 days ago

Multimodal Implementations

Comprehensive Demo of Multimodal VLMs on the Hub • 20 items • Updated about 3 hours ago • 8

upvoted 2 collections 10 days ago

FLUX.2

Our second generation of FLUX • 2 items • Updated 11 days ago • 42

Z-Image

4 items • Updated 6 days ago • 71

upvoted an article 14 days ago

Article

Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks

+2

16 days ago

•

19

upvoted a paper 14 days ago

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Paper • 2510.06961 • Published Oct 8 • 9

upvoted an article 15 days ago

Article

Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms

17 days ago

•

29

upvoted a collection 15 days ago

SAM3

5 items • Updated 17 days ago • 79

upvoted a collection 24 days ago

Meta CLIP 1

Scaling CLIP data with transparent training distribution from an end-to-end pipeline. • 7 items • Updated 12 days ago • 21

upvoted a paper 24 days ago

MetaCLIP 2: A Worldwide Scaling Recipe

Paper • 2507.22062 • Published Jul 29 • 36

upvoted a collection 26 days ago

Marvis-TTS-250m-v0.2

10 items • Updated 27 days ago • 6

upvoted an article 29 days ago

Article

Introducing AuraFace: Open-Source Face Recognition and Identity Preservation Models

Aug 26, 2024

•

52

upvoted a paper about 1 month ago

Qwen3-Omni Technical Report

Paper • 2509.17765 • Published Sep 22 • 139

upvoted 4 collections about 1 month ago

Wan2.2

5 items • Updated Sep 22 • 65

Wan2.2-diffusers

3 items • Updated Aug 25 • 14

OlmoEarth

OlmoEarth pre-trained and fine-tuned foundation models for remote sensing • 10 items • Updated 7 days ago • 14

Emu3.5

Native Multimodal Models are World Learners 🌍 • 4 items • Updated 24 days ago • 71