mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-11-25 17:29:22 +01:00
Code reuse + indication
Now shows the message in the console when unloading weights. Also reload_model() calls unload_model() first to free the memory so that multiple reloads won't overfill it.
This commit is contained in:
parent
1917b15275
commit
483d173d23
@ -64,9 +64,7 @@ def load_model_wrapper(selected_model):
|
||||
return selected_model
|
||||
|
||||
def reload_model():
|
||||
if not shared.args.cpu:
|
||||
gc.collect()
|
||||
torch.cuda.empty_cache()
|
||||
unload_model()
|
||||
shared.model, shared.tokenizer = load_model(shared.model_name)
|
||||
|
||||
def unload_model():
|
||||
@ -74,6 +72,7 @@ def unload_model():
|
||||
if not shared.args.cpu:
|
||||
gc.collect()
|
||||
torch.cuda.empty_cache()
|
||||
print("Model weights unloaded.")
|
||||
|
||||
def load_lora_wrapper(selected_lora):
|
||||
shared.lora_name = selected_lora
|
||||
|
Loading…
Reference in New Issue
Block a user