92 lines
2.2 KiB
Python
92 lines
2.2 KiB
Python
|
import os
|
||
|
|
import sys
|
||
|
|
import re
|
||
|
|
import torch
|
||
|
|
import transformers
|
||
|
|
import traceback
|
||
|
|
|
||
|
|
from queue import Queue
|
||
|
|
from threading import Thread
|
||
|
|
|
||
|
|
|
||
|
|
def post_process_output(text):
|
||
|
|
text = text.strip()
|
||
|
|
pattern = re.compile(
|
||
|
|
r"<unk>|<pad>|<s>|</s>|\[PAD\]|<\|endoftext\|>|\[UNK\]|\[CLS\]|\[MASK\]|<\|startofpiece\|>|<\|endofpiece\|>|\[gMASK\]|\[sMASK\]"
|
||
|
|
)
|
||
|
|
text = pattern.sub("", text.strip()).strip()
|
||
|
|
return text
|
||
|
|
|
||
|
|
|
||
|
|
def post_process_code(code):
|
||
|
|
sep = "\n```"
|
||
|
|
if sep in code:
|
||
|
|
blocks = code.split(sep)
|
||
|
|
if len(blocks) % 2 == 1:
|
||
|
|
for i in range(1, len(blocks), 2):
|
||
|
|
blocks[i] = blocks[i].replace("\\_", "_")
|
||
|
|
code = sep.join(blocks)
|
||
|
|
return code
|
||
|
|
|
||
|
|
|
||
|
|
class Stream(transformers.StoppingCriteria):
|
||
|
|
def __init__(self, callback_func=None):
|
||
|
|
self.callback_func = callback_func
|
||
|
|
|
||
|
|
def __call__(self, input_ids, scores) -> bool:
|
||
|
|
if self.callback_func is not None:
|
||
|
|
self.callback_func(input_ids[0])
|
||
|
|
return False
|
||
|
|
|
||
|
|
|
||
|
|
class Iteratorize:
|
||
|
|
|
||
|
|
"""
|
||
|
|
Transforms a function that takes a callback
|
||
|
|
into a lazy iterator (generator).
|
||
|
|
"""
|
||
|
|
|
||
|
|
def __init__(self, func, kwargs={}, callback=None):
|
||
|
|
self.mfunc = func
|
||
|
|
self.c_callback = callback
|
||
|
|
self.q = Queue()
|
||
|
|
self.sentinel = object()
|
||
|
|
self.kwargs = kwargs
|
||
|
|
self.stop_now = False
|
||
|
|
|
||
|
|
def _callback(val):
|
||
|
|
if self.stop_now:
|
||
|
|
raise ValueError
|
||
|
|
self.q.put(val)
|
||
|
|
|
||
|
|
def gentask():
|
||
|
|
try:
|
||
|
|
ret = self.mfunc(callback=_callback, **self.kwargs)
|
||
|
|
except ValueError:
|
||
|
|
pass
|
||
|
|
except:
|
||
|
|
traceback.print_exc()
|
||
|
|
pass
|
||
|
|
|
||
|
|
self.q.put(self.sentinel)
|
||
|
|
if self.c_callback:
|
||
|
|
self.c_callback(ret)
|
||
|
|
|
||
|
|
self.thread = Thread(target=gentask)
|
||
|
|
self.thread.start()
|
||
|
|
|
||
|
|
def __iter__(self):
|
||
|
|
return self
|
||
|
|
|
||
|
|
def __next__(self):
|
||
|
|
obj = self.q.get(True, None)
|
||
|
|
if obj is self.sentinel:
|
||
|
|
raise StopIteration
|
||
|
|
else:
|
||
|
|
return obj
|
||
|
|
|
||
|
|
def __enter__(self):
|
||
|
|
return self
|
||
|
|
|
||
|
|
def __exit__(self, exc_type, exc_val, exc_tb):
|
||
|
|
self.stop_now = True
|