Reverse-Engineered Reasoning
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
View all Papers
Organization Card
Multimodal Art Projection (M-A-P) is an open-source AI research community.
The community members are working on research topics in a wide range of spectrum, including but not limited to pre-training paradigm of foundation models, large-scale data collection and processing, and the derived applciations on coding, reasoning and music creativity.
The community is open to researchers keen on any relevant topic. Welcome to join us!
- Discord Channel
- Our Full Paper List
- mail: [email protected]
The development log of our Multimodal Art Projection (m-a-p) model family:
- π₯28/01/2025: We release YuE (δΉ), the most powerful open-source foundation models for music generation, specifically for transforming lyrics into full songs (lyrics2song), like Suno.ai. See demos.
- π₯08/05/2024: We release the fully transparent large language model MAP-Neo, series models for scaling law exploraltion and post-training alignment, and along with the training corpus Matrix.
- π₯11/04/2024: MuPT paper and demo are out. HF collection.
- π₯08/04/2024: Chinese Tiny LLM is out. HF collection.
- π₯28/02/2024: The release of ChatMusician's demo, code, model, data, and benchmark. π
- π₯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
201
m-a-p/TreePO-Qwen2.5-7B
Text Generation
β’
8B
β’
Updated
β’
83
β’
2
m-a-p/transformer_340M_baseline
0.3B
β’
Updated
β’
29
m-a-p/transformer_1.3B_baseline
1B
β’
Updated
β’
34
m-a-p/TreePO-Qwen2.5-7B_Naive2Low_Scheduler
8B
β’
Updated
β’
66
m-a-p/TreePO-Qwen2.5-7B_Low_Prob_Encourage
8B
β’
Updated
β’
68
m-a-p/TreePO-Qwen2.5-7B_GRPO-TreePO-Sampling
8B
β’
Updated
β’
71
m-a-p/TreePO-Qwen2.5-7B_fixed-div
8B
β’
Updated
β’
68
m-a-p/CriticLeanGPT-Qwen2.5-32B-RL
33B
β’
Updated
β’
68
m-a-p/CriticLeanGPT-Qwen2.5-14B-RL
15B
β’
Updated
β’
64
β’
1
m-a-p/CriticLeanGPT-Qwen2.5-7B-RL
15B
β’
Updated
β’
61
β’
1
datasets
65
m-a-p/CodeCriticBench
Preview
β’
Updated
β’
70
β’
3
m-a-p/OO1-Chat-747K
Updated
β’
3
m-a-p/PIN-200M
Preview
β’
Updated
β’
47.3k
β’
19
m-a-p/COIG-Writer
Preview
β’
Updated
β’
106
β’
21
m-a-p/Writing-Preference-Bench
Preview
β’
Updated
β’
134
β’
3
m-a-p/TreePO_data
Viewer
β’
Updated
β’
3.12k
β’
265
m-a-p/Inverse_IFEval
Viewer
β’
Updated
β’
1.01k
β’
255
β’
21
m-a-p/PIN-14M
Viewer
β’
Updated
β’
68.1k
β’
10.4k
β’
32
m-a-p/MTT
Updated
β’
861
m-a-p/DeepWriting-20K
Viewer
β’
Updated
β’
35.8k
β’
349
β’
26