AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-01 01:26:03 -04:00
Code Issues Packages Projects Releases Wiki Activity

Don't strip leading spaces in OpenAI API

Browse Source
This commit is contained in:
oobabooga 2023-11-06 19:09:41 -08:00
parent 4a45dc4041
commit 97c21e5667
1 changed files with 0 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
extensions/openai/completions.py
View File

@ -287,13 +287,7 @@ def chat_completions_common(body: dict, is_legacy: bool = False, stream=False) -
continue continue
seen_content = answer seen_content = answer
# strip extra leading space off new generated content
if len_seen == 0 and new_content[0] == ' ':
new_content = new_content[1:]
chunk = chat_streaming_chunk(new_content) chunk = chat_streaming_chunk(new_content)
yield chunk yield chunk
completion_token_count = len(encode(answer)[0]) completion_token_count = len(encode(answer)[0])
@ -390,10 +384,6 @@ def completions_common(body: dict, is_legacy: bool = False, stream=False):
for a in generator: for a in generator:
answer = a answer = a
# strip extra leading space off new generated content
if answer and answer[0] == ' ':
answer = answer[1:]
completion_token_count = len(encode(answer)[0]) completion_token_count = len(encode(answer)[0])
total_completion_token_count += completion_token_count total_completion_token_count += completion_token_count
stop_reason = "stop" stop_reason = "stop"
@ -474,19 +464,9 @@ def completions_common(body: dict, is_legacy: bool = False, stream=False):
continue continue
seen_content = answer seen_content = answer
# strip extra leading space off new generated content
if len_seen == 0 and new_content[0] == ' ':
new_content = new_content[1:]
chunk = text_streaming_chunk(new_content) chunk = text_streaming_chunk(new_content)
yield chunk yield chunk
# to get the correct count, we strip the leading space if present
if answer and answer[0] == ' ':
answer = answer[1:]
completion_token_count = len(encode(answer)[0]) completion_token_count = len(encode(answer)[0])
stop_reason = "stop" stop_reason = "stop"
if token_count + completion_token_count >= generate_params['truncation_length'] or completion_token_count >= max_tokens: if token_count + completion_token_count >= generate_params['truncation_length'] or completion_token_count >= max_tokens: