File size: 1,098 Bytes
b3ca596 feabcc6 b3ca596 5ccbdef b3ca596 ef031a5 c22d76e feabcc6 ad982b6 7de579c feabcc6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 |
import torch
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
from transformers.generation.utils import GenerationConfig
# get dtype
dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16
class EndpointHandler:
def __init__(self, path=""):
# load the model
self.model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", torch_dtype=dtype, trust_remote_code=True)
self.model.generation_config = GenerationConfig.from_pretrained(path)
self.tokenizer = AutoTokenizer.from_pretrained(path, use_fast=False, trust_remote_code=True)
def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
inputs = data.pop("inputs", data)
# ignoring parameters! Default to configs in generation_config.json.
messages = [{"role": "user", "content": inputs}]
response = self.model.chat(self.tokenizer, messages)
if torch.backends.mps.is_available():
torch.mps.empty_cache()
return [{'generated_text': response}] |