kelechic

tensorkelechi's activity

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

upvoted an article 3 days ago

view article

Article

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

• 
• 

Aug 17, 2022

•

129

liked a model 3 days ago

Qwen/Qwen3-ASR-0.6B

Automatic Speech Recognition • 0.9B • Updated Jan 30 • 411k • 272

liked a model 4 days ago

google/gemma-4-E2B

Any-to-Any • 5B • Updated 10 days ago • 62.6k • 179

liked 2 models 13 days ago

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Text-to-Speech • 2B • Updated Jan 29 • 1.32M • 1.4k

Qwen/Qwen3.5-0.8B

Image-Text-to-Text • 0.9B • Updated Mar 2 • 2.43M • 488

liked a dataset 13 days ago

nkirschi/oxford-flowers

Viewer • Updated Dec 11, 2022 • 8.19k • 2.79k • 20

liked a Space 14 days ago

Running on CPU Upgrade

Featured

3.1k

The Smol Training Playbook

📚

3.1k

The secrets to building world-class LLMs

liked a model 16 days ago

Qwen/Qwen3.5-2B

Image-Text-to-Text • 2B • Updated Mar 2 • 1.46M • 244

liked a model 21 days ago

ACE-Step/acestep-v15-base

Text-to-Audio • 2B • Updated Feb 6 • 3.29k • 59

liked a model 24 days ago

ACE-Step/acestep-transcriber

Audio-Text-to-Text • Updated Feb 3 • 3.83k • 47

liked a dataset 2 months ago

danjacobellis/musdb18HQ

Viewer • Updated Sep 8, 2024 • 650 • 362 • 2

liked a model 2 months ago

facebook/sam-audio-small

Updated Dec 30, 2025 • 3.95k • 80

upvoted an article 4 months ago

view article

Article

Continuous batching from first principles

• 
• 
• +1

Nov 25, 2025

•

356

liked 2 models 5 months ago

Qwen/Qwen2-Audio-7B-Instruct

Audio-Text-to-Text • Updated Jan 12, 2025 • 330k • 526

openai/whisper-tiny

Automatic Speech Recognition • Updated Feb 29, 2024 • 754k • 424

liked a model 6 months ago

Qwen/Qwen2.5-Omni-7B

Any-to-Any • Updated Apr 30, 2025 • 458k • 1.88k

liked 3 models 7 months ago

Qwen/Qwen2.5-Omni-3B

Any-to-Any • Updated Apr 30, 2025 • 446k • 332

Qwen/Qwen3-4B

Text Generation • Updated Jul 26, 2025 • 8.08M • 594

Qwen/Qwen3-1.7B

Text Generation • 2B • Updated Jul 26, 2025 • 8.07M • • 446

updated a collection 10 months ago

SAE

Collection

SAE models trained on music embeddings from SSL models(MuQ) and Apollo • 3 items • Updated Jun 30, 2025