Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/red-panda.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -23,6 +23,8 @@ tags:
 
 [\[🗨️ Chat Demo\]](https://internvl.opengvlab.com/)  [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL)  [\[🚀 Quick Start\]](#quick-start)  [\[📖 中文解读\]](https://zhuanlan.zhihu.com/p/706547971)  [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/)
 
+## Introduction
+
 InternVL-Chat-V1-2-Plus uses the same model architecture as [InternVL-Chat-V1-2](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-2), but the difference lies in the SFT dataset. InternVL-Chat-V1-2 only utilizes an SFT dataset with 1.2M samples, while **our plus version employs an SFT dataset with 12M samples**.
 
 <p align="center">

examples/red-panda.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d921c07bb97224d65a37801541d246067f0d506f08723ffa1ad85c217907ccb8
+size 1867237

modeling_internvl_chat.py

@@ -33,6 +33,7 @@ def version_cmp(v1, v2, op='eq'):
 class InternVLChatModel(PreTrainedModel):
     config_class = InternVLChatConfig
     main_input_name = 'pixel_values'
+    base_model_prefix = 'language_model'
     _supports_flash_attn_2 = True
     _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer']
 
@@ -97,7 +98,7 @@ class InternVLChatModel(PreTrainedModel):
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
         image_flags = image_flags.squeeze(-1)
-        input_embeds = self.language_model.get_input_embeddings()(input_ids)
+        input_embeds = self.language_model.get_input_embeddings()(input_ids).clone()
 
         vit_embeds = self.extract_feature(pixel_values)
         vit_embeds = vit_embeds[image_flags == 1]
@@ -230,8 +231,8 @@ class InternVLChatModel(PreTrainedModel):
 
         tokenizer.padding_side = 'left'
         model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
-        input_ids = model_inputs['input_ids'].cuda()
-        attention_mask = model_inputs['attention_mask'].cuda()
+        input_ids = model_inputs['input_ids'].to(self.device)
+        attention_mask = model_inputs['attention_mask'].to(self.device)
         eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
@@ -279,8 +280,8 @@ class InternVLChatModel(PreTrainedModel):
             query = query.replace('<image>', image_tokens, 1)
 
         model_inputs = tokenizer(query, return_tensors='pt')
-        input_ids = model_inputs['input_ids'].cuda()
-        attention_mask = model_inputs['attention_mask'].cuda()
+        input_ids = model_inputs['input_ids'].to(self.device)
+        attention_mask = model_inputs['attention_mask'].to(self.device)
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,