Upload folder using huggingface_hub
Browse files- VideoChat2_stage2_Mistral_7B/.gitattributes +35 -0
- VideoChat2_stage2_Mistral_7B/README.md +43 -0
- VideoChat2_stage2_Mistral_7B/videochat2_mistral_7b_stage2.pth +3 -0
- VideoChat2_stage3_Mistral_7B/.gitattributes +35 -0
- VideoChat2_stage3_Mistral_7B/.huggingface/.gitignore +1 -0
- VideoChat2_stage3_Mistral_7B/.huggingface/download/.gitattributes.lock +0 -0
- VideoChat2_stage3_Mistral_7B/.huggingface/download/.gitattributes.metadata +3 -0
- VideoChat2_stage3_Mistral_7B/.huggingface/download/README.md.lock +0 -0
- VideoChat2_stage3_Mistral_7B/.huggingface/download/README.md.metadata +3 -0
- VideoChat2_stage3_Mistral_7B/.huggingface/download/videochat2_mistral_7b_stage3.pth.lock +0 -0
- VideoChat2_stage3_Mistral_7B/.huggingface/download/videochat2_mistral_7b_stage3.pth.metadata +3 -0
- VideoChat2_stage3_Mistral_7B/README.md +43 -0
- VideoChat2_stage3_Mistral_7B/videochat2_mistral_7b_stage3.pth +3 -0
- l16_25m.pth +3 -0
- umt_l16_qformer.pth +3 -0
VideoChat2_stage2_Mistral_7B/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
VideoChat2_stage2_Mistral_7B/README.md
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
extra_gated_prompt: "You agree to not use the model to conduct experiments that cause harm to human subjects."
|
| 4 |
+
extra_gated_fields:
|
| 5 |
+
Name: text
|
| 6 |
+
Company/Organization: text
|
| 7 |
+
Country: text
|
| 8 |
+
E-Mail: text
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for VideoChat2
|
| 12 |
+
|
| 13 |
+
This modelcard aims to give the model info of 'MVBench: A Comprehensive Multi-modal Video Understanding Benchmark'.
|
| 14 |
+
|
| 15 |
+
## Model Details
|
| 16 |
+
|
| 17 |
+
### Model Sources
|
| 18 |
+
|
| 19 |
+
- **Repository:** [VideoChat2](https://github.com/OpenGVLab/Ask-Anything/tree/main/video_chat22)
|
| 20 |
+
- **Paper:** [2311.17005](https://arxiv.org/abs/2311.17005)
|
| 21 |
+
- **Point of Contact:** mailto:[InternVideo Group](gvx-sh@pjlab.org.cn)
|
| 22 |
+
|
| 23 |
+
## Citation
|
| 24 |
+
|
| 25 |
+
If you find this work useful for your research, please consider citing VideoChat2. Your acknowledgement would greatly help us in continuing to contribute resources to the research community.
|
| 26 |
+
|
| 27 |
+
```
|
| 28 |
+
@article{li2023videochat,
|
| 29 |
+
title={VideoChat: Chat-Centric Video Understanding},
|
| 30 |
+
author={KunChang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao},
|
| 31 |
+
journal={arXiv preprint arXiv:2305.06355},
|
| 32 |
+
year={2023}
|
| 33 |
+
}
|
| 34 |
+
|
| 35 |
+
@misc{li2023mvbench,
|
| 36 |
+
title={MVBench: A Comprehensive Multi-modal Video Understanding Benchmark},
|
| 37 |
+
author={Kunchang Li and Yali Wang and Yinan He and Yizhuo Li and Yi Wang and Yi Liu and Zun Wang and Jilan Xu and Guo Chen and Ping Luo and Limin Wang and Yu Qiao},
|
| 38 |
+
year={2023},
|
| 39 |
+
eprint={2311.17005},
|
| 40 |
+
archivePrefix={arXiv},
|
| 41 |
+
primaryClass={cs.CV}
|
| 42 |
+
}
|
| 43 |
+
```
|
VideoChat2_stage2_Mistral_7B/videochat2_mistral_7b_stage2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ec5cae9c06b50ab01520495f7cbca1a08df3b130d629a0078b871c71bd71cbd
|
| 3 |
+
size 1581480637
|
VideoChat2_stage3_Mistral_7B/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
VideoChat2_stage3_Mistral_7B/.huggingface/.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
*
|
VideoChat2_stage3_Mistral_7B/.huggingface/download/.gitattributes.lock
ADDED
|
File without changes
|
VideoChat2_stage3_Mistral_7B/.huggingface/download/.gitattributes.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
fdcb2d1fd931204e53e2730e7846211c91f0c464
|
| 2 |
+
a6344aac8c09253b3b630fb776ae94478aa0275b
|
| 3 |
+
1733091312.8687644
|
VideoChat2_stage3_Mistral_7B/.huggingface/download/README.md.lock
ADDED
|
File without changes
|
VideoChat2_stage3_Mistral_7B/.huggingface/download/README.md.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
fdcb2d1fd931204e53e2730e7846211c91f0c464
|
| 2 |
+
40e46ced79d1786cbdc48a9d100dda117ccc5a2e
|
| 3 |
+
1733091312.778293
|
VideoChat2_stage3_Mistral_7B/.huggingface/download/videochat2_mistral_7b_stage3.pth.lock
ADDED
|
File without changes
|
VideoChat2_stage3_Mistral_7B/.huggingface/download/videochat2_mistral_7b_stage3.pth.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
fdcb2d1fd931204e53e2730e7846211c91f0c464
|
| 2 |
+
7a13a6e129d4635789e66ef393839c32492022c2211fd8564cb46368c4973e49
|
| 3 |
+
1733091362.7773614
|
VideoChat2_stage3_Mistral_7B/README.md
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
extra_gated_prompt: "You agree to not use the model to conduct experiments that cause harm to human subjects."
|
| 4 |
+
extra_gated_fields:
|
| 5 |
+
Name: text
|
| 6 |
+
Company/Organization: text
|
| 7 |
+
Country: text
|
| 8 |
+
E-Mail: text
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for VideoChat2
|
| 12 |
+
|
| 13 |
+
This modelcard aims to give the model info of 'MVBench: A Comprehensive Multi-modal Video Understanding Benchmark'.
|
| 14 |
+
|
| 15 |
+
## Model Details
|
| 16 |
+
|
| 17 |
+
### Model Sources
|
| 18 |
+
|
| 19 |
+
- **Repository:** [VideoChat2](https://github.com/OpenGVLab/Ask-Anything/tree/main/video_chat22)
|
| 20 |
+
- **Paper:** [2311.17005](https://arxiv.org/abs/2311.17005)
|
| 21 |
+
- **Point of Contact:** mailto:[InternVideo Group](gvx-sh@pjlab.org.cn)
|
| 22 |
+
|
| 23 |
+
## Citation
|
| 24 |
+
|
| 25 |
+
If you find this work useful for your research, please consider citing VideoChat2. Your acknowledgement would greatly help us in continuing to contribute resources to the research community.
|
| 26 |
+
|
| 27 |
+
```
|
| 28 |
+
@article{li2023videochat,
|
| 29 |
+
title={VideoChat: Chat-Centric Video Understanding},
|
| 30 |
+
author={KunChang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao},
|
| 31 |
+
journal={arXiv preprint arXiv:2305.06355},
|
| 32 |
+
year={2023}
|
| 33 |
+
}
|
| 34 |
+
|
| 35 |
+
@misc{li2023mvbench,
|
| 36 |
+
title={MVBench: A Comprehensive Multi-modal Video Understanding Benchmark},
|
| 37 |
+
author={Kunchang Li and Yali Wang and Yinan He and Yizhuo Li and Yi Wang and Yi Liu and Zun Wang and Jilan Xu and Guo Chen and Ping Luo and Limin Wang and Yu Qiao},
|
| 38 |
+
year={2023},
|
| 39 |
+
eprint={2311.17005},
|
| 40 |
+
archivePrefix={arXiv},
|
| 41 |
+
primaryClass={cs.CV}
|
| 42 |
+
}
|
| 43 |
+
```
|
VideoChat2_stage3_Mistral_7B/videochat2_mistral_7b_stage3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a13a6e129d4635789e66ef393839c32492022c2211fd8564cb46368c4973e49
|
| 3 |
+
size 2074083099
|
l16_25m.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3a8f2d2898308eec48746d9596d056065650ed6d861662af689c3c3d6a82190
|
| 3 |
+
size 3878304855
|
umt_l16_qformer.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8832669b285c6b90c0996ee94d173d4ac9910e0ab266f3653c97f239d01404ea
|
| 3 |
+
size 949085085
|