ASM-FT Model Card

Model details

Model type: ASM is a unified vision-language foundation model for open-world panoptic visual recognition and understanding. Aligning with LLMs, it supports versatile generation tasks, demonstrating impressive region comprehension capability.

Model date: ASM was trained in July 2023.

Paper or resources for more information: https://github.com/OpenGVLab/all-seeing

License

ASM is open-sourced under the Apache License 2.0.

Where to send questions or comments about the model: https://github.com/OpenGVLab/all-seeing/issues

Intended use

Primary intended uses: The primary use of ASM is research on large multimodal models and chatbots.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

The pretrain phase employs AS-1B and Laion-COCO.

The finetuning phase employs AS-Core, RefCOCOg, VG, LLaVA-150K, COCO Caption, TextCaps, VQAv2, and GQA.

Evaluation dataset

A collection of 4 benchmarks, including 2 image captioning benchmarks, and 2 region captioning benchmarks.