jankin123
/

4DThinker-3B

Video-Text-to-Text

dynamic-spatial-reasoning

vision-language-model

latent-reasoning

Model card Files Files and versions

Metrics Training metrics Community

Commit History

May 11

08:46
Update model card: add metadata, library tags, and repository links (#1)⁠

jankin123 +1: nielsr

8cbfb6a
08:05
Update README.md

jankin123

Verified signature
1c9ae24

May 7

08:31
Upload 4drl/model-00002-of-00002.safetensors

chenzhangquan03

13cf9a7
08:13
Upload 4drl/model-00001-of-00002.safetensors

chenzhangquan03

2b3b27d
08:00
Upload dift/checkpoints/model-00001-of-00002.safetensors

chenzhangquan03

b65bfef
07:50
Upload dift/checkpoints/model-00002-of-00002.safetensors

chenzhangquan03

138da79
07:37
Upload 4DThinker-3B config and tokenizer files

jankin123

Verified signature
3a7d274
07:14
initial commit

jankin123

Verified signature
552da19