chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

change clip history policy

Browse Source
This commit is contained in:
qingxu fu 2023-12-15 12:52:21 +08:00
parent c181ad38b4
commit f4127a9c9c
2 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
crazy_functions/latex_fns/latex_actions.py
View File

@ -404,7 +404,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
result_pdf = pj(work_folder_modified, f'merge_diff.pdf') # get pdf path result_pdf = pj(work_folder_modified, f'merge_diff.pdf') # get pdf path
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
if modified_pdf_success: if modified_pdf_success:
yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 即将退出 ...', chatbot, history) # 刷新Gradio前端界面 yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍后 ...', chatbot, history) # 刷新Gradio前端界面
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
origin_pdf = pj(work_folder_original, f'{main_file_original}.pdf') # get pdf path origin_pdf = pj(work_folder_original, f'{main_file_original}.pdf') # get pdf path
if os.path.exists(pj(work_folder, '..', 'translation')): if os.path.exists(pj(work_folder, '..', 'translation')):

9
toolbox.py
View File

@ -1007,14 +1007,19 @@ def clip_history(inputs, history, tokenizer, max_token_limit):
def get_token_num(txt): def get_token_num(txt):
return len(tokenizer.encode(txt, disallowed_special=())) return len(tokenizer.encode(txt, disallowed_special=()))
input_token_num = get_token_num(inputs) input_token_num = get_token_num(inputs)
if max_token_limit < 5000: output_token_expect = 256 # 4k & 2k models
elif max_token_limit < 9000: output_token_expect = 512 # 8k models
else: output_token_expect = 1024 # 16k & 32k models
if input_token_num < max_token_limit * 3 / 4: if input_token_num < max_token_limit * 3 / 4:
# 当输入部分的token占比小于限制的3/4时，裁剪时 # 当输入部分的token占比小于限制的3/4时，裁剪时
# 1. 把input的余量留出来 # 1. 把input的余量留出来
max_token_limit = max_token_limit - input_token_num max_token_limit = max_token_limit - input_token_num
# 2. 把输出用的余量留出来 # 2. 把输出用的余量留出来
max_token_limit = max_token_limit - 128 max_token_limit = max_token_limit - output_token_expect
# 3. 如果余量太小了，直接清除历史 # 3. 如果余量太小了，直接清除历史
if max_token_limit < 128: if max_token_limit < output_token_expect:
history = [] history = []
return history return history
else: else: