lym0302
/

VideoLLaMA2.1-7B-AV-CoT

Visual Question Answering

videollama2_qwen2

text-generation

Audio-visual Question Answering

Audio Question Answering

multimodal large language model

Model card Files Files and versions

lym0302 commited on Mar 25

Commit

a9d202f

·

verified ·

1 Parent(s): 8e5dfd8

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "pretrained_models/VideoLLaMA2.1-7B-AV",
   "architectures": [
     "Videollama2Qwen2ForCausalLM"
   ],
@@ -15,7 +15,7 @@
   "intermediate_size": 18944,
   "max_position_embeddings": 32768,
   "max_window_layers": 28,
-  "mm_audio_tower": "pretrained_models/VideoLLaMA2.1-7B-AV/audio_tower.bin",
   "mm_hidden_size": 1152,
   "mm_hidden_size_a": 768,
   "mm_projector_a_type": "mlp2x_gelu",

 {
+  "_name_or_path": "VideoLLaMA2.1-7B-AV-CoT",
   "architectures": [
     "Videollama2Qwen2ForCausalLM"
   ],
   "intermediate_size": 18944,
   "max_position_embeddings": 32768,
   "max_window_layers": 28,
+  "mm_audio_tower": "audio_tower.bin",
   "mm_hidden_size": 1152,
   "mm_hidden_size_a": 768,
   "mm_projector_a_type": "mlp2x_gelu",