提交 65412e6c 作者: glide-the

moss_llm.py 删除 stopping_criteria

上级 ff7ac033
from abc import ABC from abc import ABC
import transformers
from langchain.llms.base import LLM from langchain.llms.base import LLM
from typing import Optional, List from typing import Optional, List
from models.loader import LoaderCheckPoint from models.loader import LoaderCheckPoint
...@@ -58,11 +57,6 @@ class MOSSLLM(BaseAnswer, LLM, ABC): ...@@ -58,11 +57,6 @@ class MOSSLLM(BaseAnswer, LLM, ABC):
history: List[List[str]] = [], history: List[List[str]] = [],
streaming: bool = False, streaming: bool = False,
generate_with_callback: AnswerResultStream = None) -> None: generate_with_callback: AnswerResultStream = None) -> None:
# Create the StoppingCriteriaList with the stopping strings
stopping_criteria_list = transformers.StoppingCriteriaList()
# 定义模型stopping_criteria 队列,在每次响应时将 torch.LongTensor, torch.FloatTensor同步到AnswerResult
listenerQueue = AnswerResultQueueSentinelTokenListenerQueue()
stopping_criteria_list.append(listenerQueue)
if len(history) > 0: if len(history) > 0:
history = history[-self.history_len:-1] if self.history_len > 0 else [] history = history[-self.history_len:-1] if self.history_len > 0 else []
prompt_w_history = str(history) prompt_w_history = str(history)
...@@ -91,8 +85,6 @@ class MOSSLLM(BaseAnswer, LLM, ABC): ...@@ -91,8 +85,6 @@ class MOSSLLM(BaseAnswer, LLM, ABC):
answer_result = AnswerResult() answer_result = AnswerResult()
answer_result.history = history answer_result.history = history
answer_result.llm_output = {"answer": response} answer_result.llm_output = {"answer": response}
if listenerQueue.listenerQueue.__len__() > 0:
answer_result.listenerToken = listenerQueue.listenerQueue.pop()
generate_with_callback(answer_result) generate_with_callback(answer_result)
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论