Shanghai_AI_Laboratory/InternVL2-1B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Add supports_gradient_checkpointing

Browse Source
This commit is contained in:
ai-modelscope
2025-03-26 15:35:47 +08:00
parent ee45ba3769
commit d0b22d04cd
3 changed files with 14 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
modeling_internvl_chat.py
View File

@@ -37,6 +37,7 @@ class InternVLChatModel(PreTrainedModel):
main_input_name = 'pixel_values'
base_model_prefix = 'language_model'
_supports_flash_attn_2 = True
supports_gradient_checkpointing = True
_no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'Qwen2DecoderLayer']
def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None, use_flash_attn=True):
@@ -346,3 +347,13 @@ class InternVLChatModel(PreTrainedModel):
)
return outputs
@property
def lm_head(self):
return self.language_model.get_output_embeddings()
def get_input_embeddings(self):
return self.language_model.get_input_embeddings()
def get_output_embeddings(self):
return self.language_model.get_output_embeddings()