Update config.json

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "pretrained_models/VideoLLaMA2.1-7B-AV",
+  "_name_or_path": "VideoLLaMA2.1-7B-AV-QA",
   "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_audio_tower": "audio_tower.bin",
   "mm_hidden_size": 1152,
   "mm_hidden_size_a": 768,
   "mm_projector_a_type": "mlp2x_gelu",
@@ -23,7 +23,7 @@
   "mm_projector_type": "stc_connector_v35",
   "mm_vision_select_feature": "patch",
   "mm_vision_select_layer": -2,
-  "mm_vision_tower": "/ailab-train/speech/liangyunming/20250212/VideoLLaMA2/siglip-so400m-patch14-384",
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
   "model_type": "videollama2_qwen2",
   "num_attention_heads": 28,
   "num_frames": 8,