DiffSynth-Studio/General-Image-Encoders

1---2frameworks:3- Pytorch4license: Apache License 2.05tags: []6tasks:7- image-text-to-text8 9#model-type:10##如 gpt、phi、llama、chatglm、baichuan 等11#- gpt12 13#domain:14##如 nlp、cv、audio、multi-modal15#- nlp16 17#language:18##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa19#- cn 20 21#metrics:22##如 CIDEr、Blue、ROUGE 等23#- CIDEr24 25#tags:26##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他27#- pretrained28 29#tools:30##如 vllm、fastchat、llamacpp、AdaSeq 等31#- vllm32---33### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。34#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型35 36SDK下载37```bash38#安装ModelScope39pip install modelscope40```41```python42#SDK模型下载43from modelscope import snapshot_download44model_dir = snapshot_download('DiffSynth-Studio/General-Image-Encoders')45```46Git下载47```48#Git模型下载49git clone https://www.modelscope.cn/DiffSynth-Studio/General-Image-Encoders.git50```51 52<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>