stanrom
/

internlm-xcomposer-7b-4bit

Feature Extraction

InternLMXComposer

Model card Files Files and versions

stanrom commited on May 21, 2024

Commit

faf3175

·

verified ·

1 Parent(s): 1821e36

Update modeling_InternLM_XComposer.py

Files changed (1) hide show

modeling_InternLM_XComposer.py +1 -1

modeling_InternLM_XComposer.py CHANGED Viewed

@@ -82,7 +82,7 @@ conversation
             # speed up init llm
             with torch.device('meta'):
                 self.internlm_model = InternLMForCausalLM._from_config(config)
-            # self.internlm_model.to_empty(device=config.device).to(torch.float16)
             # self.internlm_model.to(config.device)
             self.internlm_model.tie_weights()
         for n, m in self.internlm_model.named_modules():

             # speed up init llm
             with torch.device('meta'):
                 self.internlm_model = InternLMForCausalLM._from_config(config)
+            self.internlm_model.to_empty(device='meta').to(torch.float16)
             # self.internlm_model.to(config.device)
             self.internlm_model.tie_weights()
         for n, m in self.internlm_model.named_modules():