Hugging Face's logo

DAMO-NLP-SG
/
VideoLLaMA2-8x7B

Visual Question Answering
Transformers
Safetensors
English
videollama2_mixtral
text-generation
multimodal large language model
large video-language model
Inference Endpoints
Model card Files Community
Sicong commited on
Commit
3b74b3a
•
1 Parent(s): 7d00fed

update 72b

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -37,16 +37,18 @@ tags:
37
  | [VideoLLaMA2-7B-16F](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B-16F) | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) | 16 |
38
  | [VideoLLaMA2-8x7B-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-8x7B-Base) | Base | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | 8 |
39
  | [VideoLLaMA2-8x7B](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-8x7B) (This checkpoint) | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | 8 |
 
 
40
 
41
 
42
  ## 🚀 Main Results
43
 
44
  ### Multi-Choice Video QA & Video Captioning
45
- <p><img src="https://github.com/DAMO-NLP-SG/VideoLLaMA2/assets/18526640/9cc4a5ae-d850-4eef-bd51-83688b94698e" width="800" "/></p>
46
 
47
 
48
  ### Open-Ended Video QA
49
- <p><img src="https://github.com/DAMO-NLP-SG/VideoLLaMA2/assets/18526640/2ed7aa53-db56-4829-8375-85aefbc5120a" width="800" "/></p>
50
 
51
 
52
 
 
37
  | [VideoLLaMA2-7B-16F](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B-16F) | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) | 16 |
38
  | [VideoLLaMA2-8x7B-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-8x7B-Base) | Base | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | 8 |
39
  | [VideoLLaMA2-8x7B](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-8x7B) (This checkpoint) | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | 8 |
40
+ | [VideoLLaMA2-72B-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-72B-Base) | Base | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct) | 8 |
41
+ | [VideoLLaMA2-72B](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-72B) | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct) | 8 |
42
 
43
 
44
  ## 🚀 Main Results
45
 
46
  ### Multi-Choice Video QA & Video Captioning
47
+ <p><img src="https://github.com/user-attachments/assets/fbe3e3c2-b0f1-4e29-8b92-bc3611192909" width="800" "/></p>
48
 
49
 
50
  ### Open-Ended Video QA
51
+ <p><img src="https://github.com/user-attachments/assets/cee2efe1-309e-4301-a217-e2a848799953" width="800" "/></p>
52
 
53
 
54