File size: 566 Bytes
dcd0a52 53dc593 dcd0a52 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 |
# handler.py
from transformers import AutoModelForCausalLM, AutoTokenizer
class EndpointHandler:
def __init__(self, path=""):
self.tokenizer = AutoTokenizer.from_pretrained(path)
self.model = AutoModelForCausalLM.from_pretrained(path)
def __call__(self, data):
prompt = data["inputs"]
inputs = self.tokenizer(prompt, return_tensors="pt")
outputs = self.model.generate(**inputs, max_new_tokens=100)
response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
return {"prediction": response} |