Upload InternVideo2_cls

config.json

@@ -1,12 +1,11 @@
 {
-  "_attn_implementation_autoset": true,
   "_name_or_path": "OpenGVLab/InternVideo2-Chat-8B",
   "architectures": [
-    "InternVideo2_VideoChat2"
+    "InternVideo2_cls"
   ],
   "auto_map": {
     "AutoConfig": "model_config.VideoChat2Config",
-    "AutoModel": "OpenGVLab/InternVideo2-Chat-8B--modeling_videochat2.InternVideo2_VideoChat2"
+    "AutoModel": "modeling_videochat2_cls.InternVideo2_cls"
   },
   "model_cls": "InternVideo2_VideoChat2",
   "model_config": {

model-00007-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b89bcd9e80fdd0fa7fbe46a241ce5d61dafd4d9bcca1c27f4d525ba4cc852bfe
-size 4109221232
+oid sha256:240110bc5d108ac86d9b6032701ac1dec9c0811b2642827bfad2295cfa1d4582
+size 4117577080

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 33346282496
+    "total_size": 33354638336
   },
   "weight_map": {
     "extra_query_tokens": "model-00001-of-00007.safetensors",

modeling_videochat2_cls.py

@@ -21,23 +21,7 @@ class InternVideo2_cls(InternVideo2_VideoChat2):
                 # attn_implementation="flash_attention_2",
             )
             self.lm = AutoModelForSequenceClassification.from_config(config)
-        elif self.model_config.llm.name == 'internlm_20b':
-            from transformers import AutoModelForSequenceClassification
-            self.lm = AutoModelForSequenceClassification.from_pretrained(
-                self.model_config.llm.pretrained_llm_path,
-                torch_dtype=torch.bfloat16,
-                trust_remote_code=True,
-            )
-            self.lm.gradient_checkpointing = True
-            self.lm._set_gradient_checkpointing()
-        elif self.model_config.llm.name == 'internlm2_5_7b':
-            from transformers import AutoModelForSequenceClassification
-            self.lm = AutoModelForSequenceClassification.from_pretrained(
-                self.model_config.llm.pretrained_llm_path,
-                torch_dtype=torch.bfloat16,
-                trust_remote_code=True,
-                local_files_only=True,
-            )
+
         else:
             raise NotImplementedError(self.model_config.llm.name)
 
@@ -51,18 +35,12 @@ class InternVideo2_cls(InternVideo2_VideoChat2):
             self.use_lora = True
             from peft import get_peft_model, LoraConfig, TaskType
             logger.info("Use lora")
-            if self.model_config.llm.name == 'internlm_20b':
-                peft_config = LoraConfig(
-                    task_type=TaskType.CAUSAL_LM, inference_mode=False, 
-                    r=self.model_config.llm.lora_r, lora_alpha=self.model_config.llm.lora_alpha, lora_dropout=self.model_config.llm.lora_dropout,
-                    target_modules=['wqkv', 'wo', 'w1', 'w2', 'w3', 'output']
-                )
-            else:
-                peft_config = LoraConfig(
-                    task_type=TaskType.CAUSAL_LM, inference_mode=False, 
-                    r=self.model_config.llm.lora_r, lora_alpha=self.model_config.llm.lora_alpha, lora_dropout=self.model_config.llm.lora_dropout,
-                    target_modules=["q_proj", "k_proj", "v_proj", "o_proj",
-                                    "gate_proj", "up_proj", "down_proj", "lm_head"]
+
+            peft_config = LoraConfig(
+                task_type=TaskType.CAUSAL_LM, inference_mode=False, 
+                r=self.model_config.llm.lora_r, lora_alpha=self.model_config.llm.lora_alpha, lora_dropout=self.model_config.llm.lora_dropout,
+                target_modules=["q_proj", "k_proj", "v_proj", "o_proj",
+                                "gate_proj", "up_proj", "down_proj"]
                 )
                 
             self.lm = get_peft_model(self.lm, peft_config)