---
title: ASM-FT
canonical_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/ASM-FT"
md_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/ASM-FT.md"
repository: Shanghai_AI_Laboratory/ASM-FT
last_updated: 2024-12-30
license: apache-2.0
model_type:
  - blip-2
architectures:
  - UnifiedHuskyFlattenCatForCaption
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 1090
stars: 0
---

# ASM-FT

> ASM-FT - Shanghai_AI_Laboratory 在 ModelScope 开源的模型。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…

Shanghai_AI_Laboratory/ASM-FT 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: Shanghai_AI_Laboratory/ASM-FT
- **License**: apache-2.0
- **Downloads**: 1090
- **Stars**: 0
- **Last updated**: 2024-12-30

Source: https://www.modelscope.cn/models/Shanghai_AI_Laboratory/ASM-FT

---

# 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](https://huggingface.co/datasets/Weiyun1025/AS-100M/tree/main) and [Laion-COCO](https://huggingface.co/datasets/laion/laion-coco).

The finetuning phase employs [AS-Core](https://huggingface.co/datasets/Weiyun1025/AS-Core), [RefCOCOg](https://github.com/lichengunc/refer), [VG](https://homes.cs.washington.edu/~ranjay/visualgenome/index.html), [LLaVA-150K](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K), [COCO Caption](https://cocodataset.org/#home), [TextCaps](https://textvqa.org/textcaps/), [VQAv2](https://visualqa.org/), and [GQA](https://cs.stanford.edu/people/dorarad/gqa/).

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