mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Minor changes

Browse source
This commit is contained in:
oobabooga 2023-01-08 14:37:43 -03:00
parent 730c5562cc
commit b801e0d50d
2 changed files with 4 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

5
server.py
View file

@ -75,7 +75,7 @@ def generate_reply(question, temperature, max_length, inference_settings, select
if selected_model != model_name:
model_name = selected_model
model = None
tokenier = None
tokenizer = None
torch.cuda.empty_cache()
model, tokenizer = load_model(model_name)
if inference_settings != loaded_preset:
@ -84,8 +84,7 @@ def generate_reply(question, temperature, max_length, inference_settings, select
loaded_preset = inference_settings
torch.cuda.empty_cache()
input_text = question
input_ids = tokenizer.encode(str(input_text), return_tensors='pt').cuda()
input_ids = tokenizer.encode(str(question), return_tensors='pt').cuda()
output = eval(f"model.generate(input_ids, {preset}).cuda()")
reply = tokenizer.decode(output[0], skip_special_tokens=True)