7
EMOVA Online Interactive Demo
🔥
Live Interactive demo for EMOVA with Qwen-2.5 backbone
EMOVA-Models
A collection of EMOVA models (https://emova-ollm.github.io/)
-
-
Emova-ollm/emova-qwen-2-5-3b
Text Generation • 4B • Updated • 2 • 2 -
Emova-ollm/emova-qwen-2-5-3b-hf
Feature Extraction • 4B • Updated • 5 • 5 -
Emova-ollm/emova-qwen-2-5-7b
Text Generation • 8B • Updated • 3 • 1 -
Emova-ollm/emova-qwen-2-5-7b-hf
Feature Extraction • 8B • Updated • 54 • 2 -
Emova-ollm/emova-qwen-2-5-72b
Text Generation • 74B • Updated • 2 • 1 -
Emova-ollm/emova-qwen-2-5-72b-hf
Feature Extraction • 74B • Updated • 1 • 2 -
Emova-ollm/emova_speech_tokenizer_hf
Feature Extraction • 0.1B • Updated • 8.73k • 2 -
Emova-ollm/qwen2vit600m
Feature Extraction • 0.7B • Updated • 1.05k -
Emova-ollm/deepseek-vl2-deepseekmoe-tiny_add_speech_token_4096_nostrip
Text Generation • 3B • Updated • 1 -
Emova-ollm/deepseek-vl2-deepseekmoe-tiny
Text Generation • 3B • Updated • 35 -
Emova-ollm/Qwen2.5-7B-Instruct_add_speech_token_4096_nostrip
Feature Extraction • 7B • Updated • 5 -
Emova-ollm/Qwen2.5-3B-Instruct_add_speech_token_4096_nostrip
Text Generation • 3B • Updated • 10 -
Emova-ollm/Meta-Llama-3.1-8B-Instruct_add_speech_token_4096_nostrip-2
Feature Extraction • 8B • Updated • 1 -
EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions
Paper • 2409.18042 • Published • 41