DAMO-NLP-SG
/

VideoRefer-VideoLLaMA3-2B

Video-Text-to-Text

videollama3_qwen2

text-generation

multimodal large language model

large video-language model

Model card Files Files and versions Community

CircleRadon commited on 13 days ago

Commit

24ce314

·

verified ·

1 Parent(s): ca9508f

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/workspace/workgroup/yuanyq/code/videollama3/ProjectX_region/work_dirs/stage2_v1_10_token",
   "architectures": [
     "Videollama3Qwen2ForCausalLM"
   ],

 {
+  "_name_or_path": "VideoRefer-VideoLLaMA3-2B",
   "architectures": [
     "Videollama3Qwen2ForCausalLM"
   ],