File size: 2,080 Bytes
a6c74eb 2d3a261 a6c74eb ac360bc 9177eb5 2d3a261 9177eb5 ac360bc 9177eb5 a6c74eb ac360bc a6c74eb 28e5926 ac360bc 28e5926 ac360bc a6c74eb 28e5926 ac360bc 28e5926 a6c74eb |
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 40 41 42 43 44 45 46 47 48 |
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM, AutoModelForQuestionAnswering, AutoModel, pipeline
class EndpointHandler():
def __init__(self, path=""):
# init
# load the model
tokenizer = AutoTokenizer.from_pretrained("verseAI/vai-GPT-NeoXT-Chat-Base-20B")
model = AutoModelForCausalLM.from_pretrained("verseAI/vai-GPT-NeoXT-Chat-Base-20B", device_map="auto", load_in_8bit=True)
# THROWS ERROR model = AutoModelForQuestionAnswering.from_pretrained("verseAI/vai-GPT-NeoXT-Chat-Base-20B", device_map="auto", load_in_8bit=True)
# model = AutoModel.from_pretrained("verseAI/vai-GPT-NeoXT-Chat-Base-20B", device_map="auto", load_in_8bit=True)
# create inference pipeline
self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
#self.pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
def __call__(self, data: Dict[str, Any]) -> List[List[Dict[str, float]]]:
"""
data args:
inputs (:obj: `str`)
date (:obj: `str`)
Return:
A :obj:`list` | `dict`: will be serialized and returned
from transformers import AutoTokenizer, AutoModelForCausalLM
"""
inputs = data.pop("inputs", data)
parameters = data.pop("parameters", None)
# print(input)
# pass inputs with all kwargs in data
if parameters is not None:
prediction = self.pipeline(inputs, **parameters)
else:
prediction = self.pipeline(inputs)
# postprocess the prediction
return prediction
"""
inputs = self.tokenizer("<human>: Hello!\n<bot>:", return_tensors='pt').to(self.model.device)
outputs = self.model.generate(**inputs, max_new_tokens=10, do_sample=True, temperature=0.8)
output_str = self.tokenizer.decode(outputs[0])
print(output_str)
# return output_str
return {"generated_text": output_str}
"""
|