Spaces:
Running
Running
unify tiktoken model
Browse files
crazy_functions/Latex全文润色.py
CHANGED
@@ -13,7 +13,7 @@ class PaperFileGroup():
|
|
13 |
# count_token
|
14 |
import tiktoken
|
15 |
from toolbox import get_conf
|
16 |
-
enc = tiktoken.encoding_for_model(
|
17 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
18 |
self.get_token_num = get_token_num
|
19 |
|
|
|
13 |
# count_token
|
14 |
import tiktoken
|
15 |
from toolbox import get_conf
|
16 |
+
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
17 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
18 |
self.get_token_num = get_token_num
|
19 |
|
crazy_functions/Latex全文翻译.py
CHANGED
@@ -13,7 +13,7 @@ class PaperFileGroup():
|
|
13 |
# count_token
|
14 |
import tiktoken
|
15 |
from toolbox import get_conf
|
16 |
-
enc = tiktoken.encoding_for_model(
|
17 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
18 |
self.get_token_num = get_token_num
|
19 |
|
|
|
13 |
# count_token
|
14 |
import tiktoken
|
15 |
from toolbox import get_conf
|
16 |
+
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
17 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
18 |
self.get_token_num = get_token_num
|
19 |
|
crazy_functions/crazy_utils.py
CHANGED
@@ -4,7 +4,7 @@ from toolbox import update_ui, get_conf
|
|
4 |
def input_clipping(inputs, history, max_token_limit):
|
5 |
import tiktoken
|
6 |
import numpy as np
|
7 |
-
enc = tiktoken.encoding_for_model(
|
8 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
9 |
|
10 |
mode = 'input-and-history'
|
|
|
4 |
def input_clipping(inputs, history, max_token_limit):
|
5 |
import tiktoken
|
6 |
import numpy as np
|
7 |
+
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
8 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
9 |
|
10 |
mode = 'input-and-history'
|
crazy_functions/代码重写为全英文_多线程.py
CHANGED
@@ -61,7 +61,7 @@ def 全项目切换英文(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
|
|
61 |
MAX_TOKEN = 3000
|
62 |
import tiktoken
|
63 |
from toolbox import get_conf
|
64 |
-
enc = tiktoken.encoding_for_model(
|
65 |
def get_token_fn(txt): return len(enc.encode(txt, disallowed_special=()))
|
66 |
|
67 |
|
|
|
61 |
MAX_TOKEN = 3000
|
62 |
import tiktoken
|
63 |
from toolbox import get_conf
|
64 |
+
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
65 |
def get_token_fn(txt): return len(enc.encode(txt, disallowed_special=()))
|
66 |
|
67 |
|
crazy_functions/批量Markdown翻译.py
CHANGED
@@ -13,7 +13,7 @@ class PaperFileGroup():
|
|
13 |
# count_token
|
14 |
import tiktoken
|
15 |
from toolbox import get_conf
|
16 |
-
enc = tiktoken.encoding_for_model(
|
17 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
18 |
self.get_token_num = get_token_num
|
19 |
|
|
|
13 |
# count_token
|
14 |
import tiktoken
|
15 |
from toolbox import get_conf
|
16 |
+
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
17 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
18 |
self.get_token_num = get_token_num
|
19 |
|
crazy_functions/批量翻译PDF文档_多线程.py
CHANGED
@@ -69,7 +69,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
|
69 |
# 递归地切割PDF文件
|
70 |
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
71 |
from toolbox import get_conf
|
72 |
-
enc = tiktoken.encoding_for_model(
|
73 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
74 |
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
|
75 |
txt=file_content, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
|
|
|
69 |
# 递归地切割PDF文件
|
70 |
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
71 |
from toolbox import get_conf
|
72 |
+
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
73 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
74 |
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
|
75 |
txt=file_content, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
|
crazy_functions/理解PDF文档内容.py
CHANGED
@@ -18,7 +18,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
|
|
18 |
|
19 |
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
20 |
from toolbox import get_conf
|
21 |
-
enc = tiktoken.encoding_for_model(
|
22 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
23 |
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
|
24 |
txt=file_content, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
|
|
|
18 |
|
19 |
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
20 |
from toolbox import get_conf
|
21 |
+
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
22 |
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
23 |
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
|
24 |
txt=file_content, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
|
request_llm/bridge_chatgpt.py
CHANGED
@@ -22,8 +22,8 @@ import importlib
|
|
22 |
# config_private.py放自己的秘密如API和代理网址
|
23 |
# 读取时首先看是否存在私密的config_private配置文件(不受git管控),如果有,则覆盖原config文件
|
24 |
from toolbox import get_conf, update_ui
|
25 |
-
proxies, API_URL, API_KEY, TIMEOUT_SECONDS, MAX_RETRY
|
26 |
-
get_conf('proxies', 'API_URL', 'API_KEY', 'TIMEOUT_SECONDS', 'MAX_RETRY'
|
27 |
|
28 |
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
29 |
'网络错误,检查代理服务器是否可用,以及代理设置的格式是否正确,格式须是[协议]://[地址]:[端口],缺一不可。'
|
|
|
22 |
# config_private.py放自己的秘密如API和代理网址
|
23 |
# 读取时首先看是否存在私密的config_private配置文件(不受git管控),如果有,则覆盖原config文件
|
24 |
from toolbox import get_conf, update_ui
|
25 |
+
proxies, API_URL, API_KEY, TIMEOUT_SECONDS, MAX_RETRY = \
|
26 |
+
get_conf('proxies', 'API_URL', 'API_KEY', 'TIMEOUT_SECONDS', 'MAX_RETRY')
|
27 |
|
28 |
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
29 |
'网络错误,检查代理服务器是否可用,以及代理设置的格式是否正确,格式须是[协议]://[地址]:[端口],缺一不可。'
|