Skip to content

support internvl3 pretrain instruct #4164

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions docs/source/Instruction/支持的模型和数据集.md
Original file line number Diff line number Diff line change
Expand Up @@ -662,13 +662,34 @@
|[OpenGVLab/InternVL2_5-26B-MPO](https://modelscope.cn/models/OpenGVLab/InternVL2_5-26B-MPO)|internvl2_5|internvl2_5|transformers>=4.36, timm|✘|vision, video|[OpenGVLab/InternVL2_5-26B-MPO](https://huggingface.co/OpenGVLab/InternVL2_5-26B-MPO)|
|[OpenGVLab/InternVL2_5-38B-MPO](https://modelscope.cn/models/OpenGVLab/InternVL2_5-38B-MPO)|internvl2_5|internvl2_5|transformers>=4.36, timm|✘|vision, video|[OpenGVLab/InternVL2_5-38B-MPO](https://huggingface.co/OpenGVLab/InternVL2_5-38B-MPO)|
|[OpenGVLab/InternVL2_5-78B-MPO](https://modelscope.cn/models/OpenGVLab/InternVL2_5-78B-MPO)|internvl2_5|internvl2_5|transformers>=4.36, timm|✘|vision, video|[OpenGVLab/InternVL2_5-78B-MPO](https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO)|
|[OpenGVLab/InternVL3-1B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-1B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-1B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-1B-Pretrained)|
|[OpenGVLab/InternVL3-2B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-2B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-2B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-2B-Pretrained)|
|[OpenGVLab/InternVL3-8B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-8B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-8B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-8B-Pretrained)|
|[OpenGVLab/InternVL3-9B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-9B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-9B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-9B-Pretrained)|
|[OpenGVLab/InternVL3-14B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-14B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-14B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-14B-Pretrained)|
|[OpenGVLab/InternVL3-38B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-38B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-38B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-38B-Pretrained)|
|[OpenGVLab/InternVL3-78B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-78B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-78B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-78B-Pretrained)|
|[OpenGVLab/InternVL3-1B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-1B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-1B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-1B-Instruct)|
|[OpenGVLab/InternVL3-2B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-2B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-2B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-2B-Instruct)|
|[OpenGVLab/InternVL3-8B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-8B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-8B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-8B-Instruct)|
|[OpenGVLab/InternVL3-9B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-9B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-9B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-9B-Instruct)|
|[OpenGVLab/InternVL3-14B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-14B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-14B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-14B-Instruct)|
|[OpenGVLab/InternVL3-38B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-38B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-38B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-38B-Instruct)|
|[OpenGVLab/InternVL3-78B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-78B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-78B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-78B-Instruct)|
|[OpenGVLab/InternVL3-1B](https://modelscope.cn/models/OpenGVLab/InternVL3-1B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-1B](https://huggingface.co/OpenGVLab/InternVL3-1B)|
|[OpenGVLab/InternVL3-2B](https://modelscope.cn/models/OpenGVLab/InternVL3-2B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-2B](https://huggingface.co/OpenGVLab/InternVL3-2B)|
|[OpenGVLab/InternVL3-8B](https://modelscope.cn/models/OpenGVLab/InternVL3-8B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-8B](https://huggingface.co/OpenGVLab/InternVL3-8B)|
|[OpenGVLab/InternVL3-9B](https://modelscope.cn/models/OpenGVLab/InternVL3-9B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-9B](https://huggingface.co/OpenGVLab/InternVL3-9B)|
|[OpenGVLab/InternVL3-14B](https://modelscope.cn/models/OpenGVLab/InternVL3-14B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-14B](https://huggingface.co/OpenGVLab/InternVL3-14B)|
|[OpenGVLab/InternVL3-38B](https://modelscope.cn/models/OpenGVLab/InternVL3-38B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-38B](https://huggingface.co/OpenGVLab/InternVL3-38B)|
|[OpenGVLab/InternVL3-78B](https://modelscope.cn/models/OpenGVLab/InternVL3-78B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-78B](https://huggingface.co/OpenGVLab/InternVL3-78B)|
|[OpenGVLab/InternVL3-1B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-1B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-1B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-1B-AWQ)|
|[OpenGVLab/InternVL3-2B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-2B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-2B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-2B-AWQ)|
|[OpenGVLab/InternVL3-8B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-8B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-8B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-8B-AWQ)|
|[OpenGVLab/InternVL3-9B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-9B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-9B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-9B-AWQ)|
|[OpenGVLab/InternVL3-14B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-14B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-14B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-14B-AWQ)|
|[OpenGVLab/InternVL3-38B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-38B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-38B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-38B-AWQ)|
|[OpenGVLab/InternVL3-78B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-78B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-78B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-78B-AWQ)|
|[Shanghai_AI_Laboratory/internlm-xcomposer2-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2-7b)|xcomposer2|ixcomposer2|-|✘|vision|[internlm/internlm-xcomposer2-7b](https://huggingface.co/internlm/internlm-xcomposer2-7b)|
|[Shanghai_AI_Laboratory/internlm-xcomposer2-4khd-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2-4khd-7b)|xcomposer2_4khd|ixcomposer2|-|✘|vision|[internlm/internlm-xcomposer2-4khd-7b](https://huggingface.co/internlm/internlm-xcomposer2-4khd-7b)|
|[Shanghai_AI_Laboratory/internlm-xcomposer2d5-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2d5-7b)|xcomposer2_5|xcomposer2_5|decord|✘|vision|[internlm/internlm-xcomposer2d5-7b](https://huggingface.co/internlm/internlm-xcomposer2d5-7b)|
Expand Down
21 changes: 21 additions & 0 deletions docs/source_en/Instruction/Supported-models-and-datasets.md
Original file line number Diff line number Diff line change
Expand Up @@ -662,13 +662,34 @@ The table below introduces the models integrated with ms-swift:
|[OpenGVLab/InternVL2_5-26B-MPO](https://modelscope.cn/models/OpenGVLab/InternVL2_5-26B-MPO)|internvl2_5|internvl2_5|transformers>=4.36, timm|✘|vision, video|[OpenGVLab/InternVL2_5-26B-MPO](https://huggingface.co/OpenGVLab/InternVL2_5-26B-MPO)|
|[OpenGVLab/InternVL2_5-38B-MPO](https://modelscope.cn/models/OpenGVLab/InternVL2_5-38B-MPO)|internvl2_5|internvl2_5|transformers>=4.36, timm|✘|vision, video|[OpenGVLab/InternVL2_5-38B-MPO](https://huggingface.co/OpenGVLab/InternVL2_5-38B-MPO)|
|[OpenGVLab/InternVL2_5-78B-MPO](https://modelscope.cn/models/OpenGVLab/InternVL2_5-78B-MPO)|internvl2_5|internvl2_5|transformers>=4.36, timm|✘|vision, video|[OpenGVLab/InternVL2_5-78B-MPO](https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO)|
|[OpenGVLab/InternVL3-1B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-1B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-1B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-1B-Pretrained)|
|[OpenGVLab/InternVL3-2B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-2B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-2B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-2B-Pretrained)|
|[OpenGVLab/InternVL3-8B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-8B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-8B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-8B-Pretrained)|
|[OpenGVLab/InternVL3-9B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-9B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-9B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-9B-Pretrained)|
|[OpenGVLab/InternVL3-14B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-14B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-14B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-14B-Pretrained)|
|[OpenGVLab/InternVL3-38B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-38B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-38B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-38B-Pretrained)|
|[OpenGVLab/InternVL3-78B-Pretrained](https://modelscope.cn/models/OpenGVLab/InternVL3-78B-Pretrained)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-78B-Pretrained](https://huggingface.co/OpenGVLab/InternVL3-78B-Pretrained)|
|[OpenGVLab/InternVL3-1B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-1B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-1B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-1B-Instruct)|
|[OpenGVLab/InternVL3-2B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-2B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-2B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-2B-Instruct)|
|[OpenGVLab/InternVL3-8B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-8B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-8B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-8B-Instruct)|
|[OpenGVLab/InternVL3-9B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-9B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-9B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-9B-Instruct)|
|[OpenGVLab/InternVL3-14B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-14B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-14B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-14B-Instruct)|
|[OpenGVLab/InternVL3-38B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-38B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-38B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-38B-Instruct)|
|[OpenGVLab/InternVL3-78B-Instruct](https://modelscope.cn/models/OpenGVLab/InternVL3-78B-Instruct)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-78B-Instruct](https://huggingface.co/OpenGVLab/InternVL3-78B-Instruct)|
|[OpenGVLab/InternVL3-1B](https://modelscope.cn/models/OpenGVLab/InternVL3-1B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-1B](https://huggingface.co/OpenGVLab/InternVL3-1B)|
|[OpenGVLab/InternVL3-2B](https://modelscope.cn/models/OpenGVLab/InternVL3-2B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-2B](https://huggingface.co/OpenGVLab/InternVL3-2B)|
|[OpenGVLab/InternVL3-8B](https://modelscope.cn/models/OpenGVLab/InternVL3-8B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-8B](https://huggingface.co/OpenGVLab/InternVL3-8B)|
|[OpenGVLab/InternVL3-9B](https://modelscope.cn/models/OpenGVLab/InternVL3-9B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-9B](https://huggingface.co/OpenGVLab/InternVL3-9B)|
|[OpenGVLab/InternVL3-14B](https://modelscope.cn/models/OpenGVLab/InternVL3-14B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-14B](https://huggingface.co/OpenGVLab/InternVL3-14B)|
|[OpenGVLab/InternVL3-38B](https://modelscope.cn/models/OpenGVLab/InternVL3-38B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-38B](https://huggingface.co/OpenGVLab/InternVL3-38B)|
|[OpenGVLab/InternVL3-78B](https://modelscope.cn/models/OpenGVLab/InternVL3-78B)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-78B](https://huggingface.co/OpenGVLab/InternVL3-78B)|
|[OpenGVLab/InternVL3-1B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-1B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-1B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-1B-AWQ)|
|[OpenGVLab/InternVL3-2B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-2B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-2B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-2B-AWQ)|
|[OpenGVLab/InternVL3-8B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-8B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-8B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-8B-AWQ)|
|[OpenGVLab/InternVL3-9B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-9B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-9B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-9B-AWQ)|
|[OpenGVLab/InternVL3-14B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-14B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-14B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-14B-AWQ)|
|[OpenGVLab/InternVL3-38B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-38B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-38B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-38B-AWQ)|
|[OpenGVLab/InternVL3-78B-AWQ](https://modelscope.cn/models/OpenGVLab/InternVL3-78B-AWQ)|internvl3|internvl2_5|transformers>=4.37.2, timm|✘|vision, video|[OpenGVLab/InternVL3-78B-AWQ](https://huggingface.co/OpenGVLab/InternVL3-78B-AWQ)|
|[Shanghai_AI_Laboratory/internlm-xcomposer2-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2-7b)|xcomposer2|ixcomposer2|-|✘|vision|[internlm/internlm-xcomposer2-7b](https://huggingface.co/internlm/internlm-xcomposer2-7b)|
|[Shanghai_AI_Laboratory/internlm-xcomposer2-4khd-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2-4khd-7b)|xcomposer2_4khd|ixcomposer2|-|✘|vision|[internlm/internlm-xcomposer2-4khd-7b](https://huggingface.co/internlm/internlm-xcomposer2-4khd-7b)|
|[Shanghai_AI_Laboratory/internlm-xcomposer2d5-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2d5-7b)|xcomposer2_5|xcomposer2_5|decord|✘|vision|[internlm/internlm-xcomposer2d5-7b](https://huggingface.co/internlm/internlm-xcomposer2d5-7b)|
Expand Down
31 changes: 31 additions & 0 deletions swift/llm/model/model/internlm.py
Original file line number Diff line number Diff line change
Expand Up @@ -280,6 +280,27 @@ def get_model_tokenizer_internvl(model_dir: str,
ModelMeta(
MLLMModelType.internvl3,
[
# pretrain
ModelGroup([
Model('OpenGVLab/InternVL3-1B-Pretrained', 'OpenGVLab/InternVL3-1B-Pretrained'),
Model('OpenGVLab/InternVL3-2B-Pretrained', 'OpenGVLab/InternVL3-2B-Pretrained'),
Model('OpenGVLab/InternVL3-8B-Pretrained', 'OpenGVLab/InternVL3-8B-Pretrained'),
Model('OpenGVLab/InternVL3-9B-Pretrained', 'OpenGVLab/InternVL3-9B-Pretrained'),
Model('OpenGVLab/InternVL3-14B-Pretrained', 'OpenGVLab/InternVL3-14B-Pretrained'),
Model('OpenGVLab/InternVL3-38B-Pretrained', 'OpenGVLab/InternVL3-38B-Pretrained'),
Model('OpenGVLab/InternVL3-78B-Pretrained', 'OpenGVLab/InternVL3-78B-Pretrained'),
]),
# instruct
ModelGroup([
Model('OpenGVLab/InternVL3-1B-Instruct', 'OpenGVLab/InternVL3-1B-Instruct'),
Model('OpenGVLab/InternVL3-2B-Instruct', 'OpenGVLab/InternVL3-2B-Instruct'),
Model('OpenGVLab/InternVL3-8B-Instruct', 'OpenGVLab/InternVL3-8B-Instruct'),
Model('OpenGVLab/InternVL3-9B-Instruct', 'OpenGVLab/InternVL3-9B-Instruct'),
Model('OpenGVLab/InternVL3-14B-Instruct', 'OpenGVLab/InternVL3-14B-Instruct'),
Model('OpenGVLab/InternVL3-38B-Instruct', 'OpenGVLab/InternVL3-38B-Instruct'),
Model('OpenGVLab/InternVL3-78B-Instruct', 'OpenGVLab/InternVL3-78B-Instruct'),
]),
# mpo
ModelGroup([
Model('OpenGVLab/InternVL3-1B', 'OpenGVLab/InternVL3-1B'),
Model('OpenGVLab/InternVL3-2B', 'OpenGVLab/InternVL3-2B'),
Expand All @@ -289,6 +310,16 @@ def get_model_tokenizer_internvl(model_dir: str,
Model('OpenGVLab/InternVL3-38B', 'OpenGVLab/InternVL3-38B'),
Model('OpenGVLab/InternVL3-78B', 'OpenGVLab/InternVL3-78B'),
]),
# awq (Use lmdeploy for inference.)
ModelGroup([
Model('OpenGVLab/InternVL3-1B-AWQ', 'OpenGVLab/InternVL3-1B-AWQ'),
Model('OpenGVLab/InternVL3-2B-AWQ', 'OpenGVLab/InternVL3-2B-AWQ'),
Model('OpenGVLab/InternVL3-8B-AWQ', 'OpenGVLab/InternVL3-8B-AWQ'),
Model('OpenGVLab/InternVL3-9B-AWQ', 'OpenGVLab/InternVL3-9B-AWQ'),
Model('OpenGVLab/InternVL3-14B-AWQ', 'OpenGVLab/InternVL3-14B-AWQ'),
Model('OpenGVLab/InternVL3-38B-AWQ', 'OpenGVLab/InternVL3-38B-AWQ'),
Model('OpenGVLab/InternVL3-78B-AWQ', 'OpenGVLab/InternVL3-78B-AWQ'),
]),
],
TemplateType.internvl2_5,
get_model_tokenizer_internvl,
Expand Down
Loading