The checkpoints for the MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training.
Multimodal Art Projection
community
AI & ML interests
None defined yet.
Organization Card
About org cards
Multimodal Art Projection (M-A-P) is an opensource research community. The coummnity members are working on Artificial Intelligence-Generated Content (AIGC) topics, including text, audio, and vision modalities. We do large language/music/multimodal models (LLMs/LMMs) training, data collection, and development of fun applications.
Welcome to join us!
Organization page: https://m-a-p.ai
The development log of our Multimodal Art Projection (m-a-p) model family:
- 🔥11/04/2024: MuPT paper and demo are out. HF collection.
- 🔥08/04/2024: Chinese Tiny LLM is out. HF collection.
- 🔥28/02/2024: The release of ChatMusician's demo, code, model, data, and benchmark. 😆
- 🔥23/02/2024: The release of OpenCodeInterpreter, beats GPT-4 code interpreter on HumanEval.
- 23/01/2024: we release CMMMU for better Chinese LMMs' Evaluation.
- 13/01/2024: we release a series of Music Pretrained Transformer (MuPT) checkpoints, with size up to 1.3B and 8192 context length. Our models are LLAMA2-based, pre-trained on world's largest 10B tokens symbolic music dataset (ABC notation format). We currently support Megatron-LM format and will release huggingface checkpoints soon.
- 02/06/2023: officially release the MERT pre-print paper and training codes.
- 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M , trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks.
- 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public
- 29/12/2022: a music understanding model MERT-v0 trained with MLM paradigm, which performs better at downstream tasks.
- 29/10/2022: a pre-trained MIR model music2vec trained with BYOL paradigm.
models
91
m-a-p/MERT-v1-330M
Feature Extraction
•
Updated
•
32k
•
33
m-a-p/MERT-v1-95M
Feature Extraction
•
Updated
•
18.7k
•
16
m-a-p/MusiLingo-musicqa-v1
Feature Extraction
•
Updated
•
12
m-a-p/MusiLingo-long-v1
Feature Extraction
•
Updated
•
36
•
2
m-a-p/MusiLingo-short-v1
Feature Extraction
•
Updated
•
17
•
1
m-a-p/MuPT-v1-8192-550M
Text Generation
•
Updated
•
20
•
1
m-a-p/MuPT-v1-8192-190M
Text Generation
•
Updated
•
97
•
1
m-a-p/MuPT-v1-8192-1.07B
Text Generation
•
Updated
•
13
•
2
m-a-p/MuPT-v1.1-8192-1.07B
Text Generation
•
Updated
m-a-p/MuPT-v1.1-8192-1.97B
Text Generation
•
Updated
datasets
14
m-a-p/COIG-CQIA
Viewer
•
Updated
•
1.25k
•
373
m-a-p/MAP-CC
Viewer
•
Updated
•
27
•
39
m-a-p/COIG-Kun
Viewer
•
Updated
•
52
•
22
m-a-p/CHC-Bench
Viewer
•
Updated
•
5
m-a-p/CodeEditorBench
Preview
•
Updated
•
7
•
15
m-a-p/CMMMU
Viewer
•
Updated
•
163
•
26
m-a-p/MusicPile
Viewer
•
Updated
•
11
•
24
m-a-p/MusicPile-sft
Viewer
•
Updated
•
82
•
9
m-a-p/MusicTheoryBench
Viewer
•
Updated
•
3
•
6
m-a-p/CodeFeedback-Filtered-Instruction
Viewer
•
Updated
•
1.24k
•
71