metadata
license: apache-2.0
language:
- en
metrics:
- accuracy
base_model:
- meta-llama/Llama-3.1-8B-Instruct
pipeline_tag: visual-question-answering
MMEvol Model Card
Model Details
Here are the pretrained weights and instruction tuning weights
| Model | Pretrained Projector | Base LLM | PT Data | IT Data | Download |
|---|---|---|---|---|---|
| MMEvol-LLaMA3-8B | mm_projector | LLaMA3-8B | LLaVA-Pretrain | MMEvol | ckpt |
Training dataset
Performance
VLMEvalKit Support (OpenCompass)
| Model | MME_C | MMStar | HallBench | MathVista_mini | MMMU_val | AI2D | POPE | BLINK | RWQA |
|---|---|---|---|---|---|---|---|---|---|
| MMEvol-LLaMA3-8B | 47.8 | 50.1 | 62.3 | 50.0 | 40.8 | 73.9 | 86.8 | 46.4 | 62.6 |
VLMEvalKit Not Support (VQADataSet)
| Model | VQA_v2 | GQA | MIA | MMSInst |
|---|---|---|---|---|
| MMEvol-LLaMA3-8B | 83.4 | 65.0 | 78.8 | 32.3 |
Paper or resources for more information
License
Llama 3 is licensed under the LLAMA 3 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
Contact us if you have any questions
- Run Luo — r.luo@siat.ac.cn
- Haonan Zhang — zchiowal@gmail.com