File size: 1,361 Bytes
c591244 |
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 36 37 38 39 |
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16
class EndpointHandler:
def __init__(self, path=""):
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
path,
return_dict=True,
device_map="auto",
load_in_8bit=True,
torch_dtype=dtype,
trust_remote_code=True,
)
generation_config=model_quantized.generation_config
generation_config.max_new_token=60
generation_config.temperature=0.7
generation_config.num_return_sequence=1
generation_config.pad_token_id=tokenizer.eos_token_id
generation_config.eos_token_id=tokenizer.eos_token_id
generation_config.max_length=50
self.generation_config = generation_config
self.pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer
)
def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
prompt = data.pop("inputs", data)
result = self.pipeline(prompt, generation_config=self.generation_config)
return result |