LLaMA-LoRA-Tuner-UI-Demo / llama_lora /lib /streaming_generation_utils.py
zetavg
extract inference
4870204
"""
Helpers to support streaming generate output.
Borrowed from https://github.com/oobabooga/text-generation-webui/blob/ad37f396fc8bcbab90e11ecf17c56c97bfbd4a9c/modules/callbacks.py
"""
import gc
import traceback
from queue import Queue
from threading import Thread
import torch
import transformers
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