Upload InternVideo2_Classification_test

config.json

@@ -1,54 +1,52 @@
 {
-  "_attn_implementation_autoset": true,
-  "_name_or_path": "OpenGVLab/InternVideo2-Chat-8B",
+  "architectures": [
+    "InternVideo2_Classification_test"
+  ],
   "auto_map": {
-    "AutoConfig": "model_config.VideoChat2Config"
+    "AutoModel": "modeling_videochat2_classification.InternVideo2_Classification_test"
   },
-  "model_config": {
-    "bridge": {
-      "extra_num_query_token": 64,
-      "name": "qformer",
-      "num_query_token": 32,
-      "qformer_attention_probs_dropout_prob": 0.1,
-      "qformer_drop_path_rate": 0.2,
-      "qformer_hidden_dropout_prob": 0.1
-    },
-    "freeze_bridge": false,
-    "freeze_llm": false,
-    "freeze_vision_encoder": false,
-    "llm": {
-      "lora_alpha": 32,
-      "lora_dropout": 0.1,
-      "lora_r": 16,
-      "name": "mistral_7b",
-      "pretrained_llm_path": "mistralai/Mistral-7B-Instruct-v0.3",
-      "use_lora": true
-    },
-    "loss": {
-      "use_vision_regression_loss": false
-    },
-    "pretrained_paths": {},
-    "use_flash_attention": true,
-    "vision_encoder": {
-      "checkpoint_num": 48,
-      "d_model": 1408,
-      "encoder_embed_dim": 1408,
-      "img_size": 224,
-      "name": "internvideo2-1B",
-      "num_frames": 8,
-      "origin_num_frames": 4,
-      "patch_size": 14,
-      "pretrained": null,
-      "sep_image_video_pos_embed": true,
-      "tubelet_size": 1,
-      "use_checkpoint": true,
-      "vit_add_ln": true,
-      "x_vis_only": true,
-      "x_vis_return_idx": -2
-    }
+  "bridge": {
+    "extra_num_query_token": 64,
+    "name": "qformer",
+    "num_query_token": 32,
+    "qformer_attention_probs_dropout_prob": 0.1,
+    "qformer_drop_path_rate": 0.2,
+    "qformer_hidden_dropout_prob": 0.1
   },
-  "model_type": "InternVideo2_VideoChat2",
+  "freeze_bridge": false,
+  "freeze_llm": false,
+  "freeze_vision_encoder": false,
+  "llm": {
+    "lora_alpha": 32,
+    "lora_dropout": 0.1,
+    "lora_r": 16,
+    "name": "mistral_7b",
+    "pretrained_llm_path": "mistralai/Mistral-7B-Instruct-v0.3",
+    "use_lora": true
+  },
+  "loss": {
+    "use_vision_regression_loss": false
+  },
+  "model_type": "InternVideo2_VideoChat2_test",
+  "pretrained_paths": {},
   "torch_dtype": "float32",
   "transformers_version": "4.46.1",
-  "use_cache": true
+  "use_flash_attention": true,
+  "vision_encoder": {
+    "checkpoint_num": 48,
+    "d_model": 1408,
+    "encoder_embed_dim": 1408,
+    "img_size": 224,
+    "name": "internvideo2-1B",
+    "num_frames": 8,
+    "origin_num_frames": 4,
+    "patch_size": 14,
+    "pretrained": null,
+    "sep_image_video_pos_embed": true,
+    "tubelet_size": 1,
+    "use_checkpoint": true,
+    "vit_add_ln": true,
+    "x_vis_only": true,
+    "x_vis_return_idx": -2
+  }
 }

modeling_videochat2_classification.py

@@ -388,14 +388,15 @@ class InternVideo2_Classification(PreTrainedModel):
 class InternVideo2_Classification_test(PreTrainedModel):
     config_class = VideoChat2Config
     def __init__(self, config):
-        self.model_config = config.model_config
-        # config.model_config = None
         super().__init__(config)
         self.w = torch.randn(10,10, requires_grad=True)
 
 
     def forward(self, x):
         return x
+    
+    def test_lol(self, x):
+        return x
 
 if __name__ == "__main__":