File size: 1,138 Bytes
5f6dd19 d217cb5 5f6dd19 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 |
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from typing import Dict, List, Any
class EndpointHandler:
# def __init__(self, path="decapoda-research/llama-65b-hf"):
def __init__(self, path="TangrisJones/vicuna-13b-GPTQ-4bit-128g"):
self.tokenizer = AutoTokenizer.from_pretrained(path)
self.model = AutoModelForCausalLM.from_pretrained(path)
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
input_text = data["inputs"]
kwargs = data.get("kwargs", {})
# Tokenize input text
input_tokens = self.tokenizer.encode(input_text, return_tensors="pt")
# Generate output tokens
with torch.no_grad():
output_tokens = self.model.generate(input_tokens, **kwargs)
# Decode output tokens
output_text = self.tokenizer.decode(output_tokens[0])
return [{"output": output_text}]
# Example usage
if __name__ == "__main__":
handler = EndpointHandler()
input_data = {"inputs": "Once upon a time in a small village, "}
output_data = handler(input_data)
print(output_data)
|