Location of model and tokenizer
#22
by Dm124r - opened
Hello, I have a problem whan i use next ptompt:
mname = "facebook/blenderbot-400M-distill"
model = BlenderbotForConditionalGeneration.from_pretrained(mname)
tokenizer = BlenderbotTokenizer.from_pretrained(mname)
UTTERANCE = "Hi"
inputs = tokenizer([UTTERANCE], return_tensors="pt")
reply_ids = model.generate(**inputs)
print(tokenizer.batch_decode(reply_ids))
Are model and tokenizer downloaded every time we ask the model to generate a response?
How i can find the location of model and tokenizer after downloading?
I use it in python project with venv.