-
LGAI-EXAONE/EXAONE-4.0-1.2B
Text Generation • 1B • Updated • 82.9k • 172 -
mistralai/Voxtral-Mini-4B-Realtime-2602
Automatic Speech Recognition • 4B • Updated • 580k • 697 -
Qwen/Qwen3-ASR-0.6B
Automatic Speech Recognition • Updated • 330k • 234 -
Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents
Paper • 2509.26539 • Published • 10
Eugene Oskin
eoskin
AI & ML interests
None yet
Recent Activity
upvoted an article about 21 hours ago
Introducing Storage Buckets on the Hugging Face Hub liked
a model 2 days ago
lmstudio-community/Qwen3-Coder-Next-MLX-4bit liked
a model 2 days ago
deepseek-ai/DeepSeek-V3-Base Organizations
None yet
-
Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning
Paper • 2311.11077 • Published • 29 -
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 90 -
LoRA: Low-Rank Adaptation of Large Language Models
Paper • 2106.09685 • Published • 59 -
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Paper • 2403.03853 • Published • 66
-
LGAI-EXAONE/EXAONE-4.0-1.2B
Text Generation • 1B • Updated • 82.9k • 172 -
mistralai/Voxtral-Mini-4B-Realtime-2602
Automatic Speech Recognition • 4B • Updated • 580k • 697 -
Qwen/Qwen3-ASR-0.6B
Automatic Speech Recognition • Updated • 330k • 234 -
Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents
Paper • 2509.26539 • Published • 10
-
Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning
Paper • 2311.11077 • Published • 29 -
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 90 -
LoRA: Low-Rank Adaptation of Large Language Models
Paper • 2106.09685 • Published • 59 -
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Paper • 2403.03853 • Published • 66