Karel Minarik

karmiq's activity

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

liked 2 Spaces about 1 month ago

Running on Zero

83

83

STAR

🌟

Video Super-Resolution with Text-to-Video Model

Running on Zero

769

769

Whisper Turbo

🤯

Transcribe or translate audio and YouTube videos

liked 3 models about 2 months ago

mlx-community/QVQ-72B-Preview-8bit

Image-Text-to-Text • Updated Dec 24, 2024 • 42 • 3

tomaarsen/ModernBERT-base-gooaq

Sentence Similarity • Updated Dec 19, 2024 • 2.26k • 15

Datou1111/shou_xin

Text-to-Image • Updated Dec 9, 2024 • 2.66k • 857

liked 2 Spaces 2 months ago

Running on CPU Upgrade

7.28k

7.28k

Kolors Virtual Try-On

👕

Virtual try-on for clothes on a person

Running on Zero

419

419

Flux Fill Outpainting

👈

Extend images using prompts and alignment options

liked a dataset 2 months ago

ylecun/mnist

Viewer • Updated Aug 8, 2024 • 70k • 33.7k • 154

liked a Space 3 months ago

Running on L40S

137

137

Flux IP Adapter

🖼

Prompt with Images in flux[dev]

liked a model 3 months ago

mlx-community/whisper-large-v3-turbo

Updated Nov 1, 2024 • 2.3k • 45

upvoted an article 4 months ago

view article

Article

🇨🇿 BenCzechMark - Can your LLM Understand Czech?

Oct 1, 2024

• 19

updated a collection 8 months ago

Search

Collection

8 items • Updated Jun 27, 2024

upvoted a paper 8 months ago

Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation

Paper • 2406.16678 • Published Jun 24, 2024 • 16

liked a model 8 months ago

nvidia/Nemotron-4-340B-Instruct

Updated Jun 24, 2024 • 109 • 669

upvoted a collection 8 months ago

Nemotron 4 340B

Collection

Nemotron-4: open models for Synthetic Data Generation (SDG). Includes Base, Instruct, and Reward models. • 4 items • Updated 23 days ago • 161

liked a dataset 8 months ago

TIGER-Lab/MMLU-Pro

Viewer • Updated Nov 27, 2024 • 12.1k • 45.2k • 314

updated a collection 8 months ago

LLM

Collection

23 items • Updated Jun 4, 2024

upvoted a paper 8 months ago

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Paper • 2406.01574 • Published Jun 3, 2024 • 45

liked a Space 8 months ago

Running

636

636

FineWeb: decanting the web for the finest text data at scale

🍷

Generate high-quality web text data for LLM training

upvoted an article 9 months ago

view article

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28, 2024

• 179