AI & ML interests
Multimodal LLM
Recent Activity
Organization Card
[2024-09-06] ππ We release
VITA, including the training code, deployment code, and model weights.
models
20
VITA-MLLM/VITA-E
Updated
β’
1
VITA-MLLM/VITA-Audio-Plus-Boost
11B
β’
Updated
β’
13
β’
3
VITA-MLLM/VITA-Audio-Boost
10B
β’
Updated
β’
13
β’
3
VITA-MLLM/VITA-Audio-Plus-Vanilla
8B
β’
Updated
β’
202
β’
5
VITA-MLLM/VITA-Audio-Balance
10B
β’
Updated
β’
8
β’
3
VITA-MLLM/Long-VITA-1M_HF
15B
β’
Updated
β’
2
β’
1
VITA-MLLM/Long-VITA-1M_MG
Updated
β’
1
VITA-MLLM/Long-VITA-1M
Updated
β’
8
VITA-MLLM/Long-VITA-128K_HF
15B
β’
Updated
β’
1
β’
1
VITA-MLLM/Long-VITA-128K_MG
Updated
β’
1
datasets
6
VITA-MLLM/VITA-Audio-Data
Preview
β’
Updated
β’
50
β’
7
VITA-MLLM/Emotion_NaturalConv_FunctionCall
Preview
β’
Updated
β’
80
β’
1
VITA-MLLM/AudioQA-1M
Preview
β’
Updated
β’
216
β’
3
VITA-MLLM/Comic-9K
Viewer
β’
Updated
β’
239k
β’
157
β’
6
VITA-MLLM/MovieNet-Summary
Updated
β’
9
β’
2
VITA-MLLM/Long-VITA-Data
Viewer
β’
Updated
β’
17.8M
β’
68
β’
2