Hugging Face's logo

Zhang199
/
TinyLLaVA-Video-R1

Video-Text-to-Text
Transformers
TensorBoard
Safetensors
tinyllava
text-generation
Model card Files
xet
Metrics Community
2
Zhang199 commited on
Commit
43a4bad
·
verified ·
1 Parent(s): 28a1978

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -10,6 +10,6 @@ pipeline_tag: image-text-to-text
10
  Here, we introduce a small-scale video reasoning model TinyLLaVA-Video-R1, based on the traceably trained model [TinyLLaVA-Video](https://github.com/ZhangXJ199/TinyLLaVA-Video). After reinforcement learning on general Video-QA datasets, the model not only significantly improves its reasoning and thinking abilities, but also exhibits the emergent characteristic of “aha moments”.
11
 
12
  ### Result
13
- | Model (HF Path) | Video-MME | MVBench | MLVU | MMVU |
14
  | :----------------------------------------: | ------------- | ------- | -------------- | ---------- |
15
- | [Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512](https://huggingface.co/Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512) | 46.6 | 49.5 | 52.4 | 46.9 |
 
10
  Here, we introduce a small-scale video reasoning model TinyLLaVA-Video-R1, based on the traceably trained model [TinyLLaVA-Video](https://github.com/ZhangXJ199/TinyLLaVA-Video). After reinforcement learning on general Video-QA datasets, the model not only significantly improves its reasoning and thinking abilities, but also exhibits the emergent characteristic of “aha moments”.
11
 
12
  ### Result
13
+ | Model (HF Path) | Video-MME | MVBench | MLVU | MMVU |
14
  | :----------------------------------------: | ------------- | ------- | -------------- | ---------- |
15
+ | [Zhang199/TinyLLaVA-Video-R1](https://huggingface.co/Zhang199/TinyLLaVA-Video-R1) | 46.6 | 49.5 | 52.4 | 46.9 |