weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

moss_llm.py 删除 stopping_criteria

This commit is contained in:
glide-the 2023-05-19 23:47:13 +08:00
parent ff7ac0333e
commit 65412e6cfb
1 changed files with 0 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
models/moss_llm.py
View File

@ -1,5 +1,4 @@
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):
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):
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)