mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Fix partial unicode characters issue (#4837)

Browse source
This commit is contained in:
Yiximail 2023-12-08 20:50:53 +08:00 • committed by GitHub
parent 2c5a1e67f9
commit 1c74b3ab45
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 33 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

19
modules/exllama.py
View file

@ -165,10 +165,19 @@ class ExllamaModel:
if has_leading_space:
decoded_text = ' ' + decoded_text
yield decoded_text
# Check the partial unicode character
if chr(0xfffd) in decoded_text:
is_last = i == max_new_tokens - 1
is_stopping = token.item() == self.generator.tokenizer.eos_token_id or shared.stop_everything
# If we are not at the end of the generation, we skip this token
if not (is_last or is_stopping):
continue
if token.item() == self.generator.tokenizer.eos_token_id or shared.stop_everything:
break
yield decoded_text
# Case 2: CFG
# Copied from https://github.com/turboderp/exllama/blob/master/example_cfg.py
else:
@ -205,6 +214,14 @@ class ExllamaModel:
if has_leading_space:
decoded_text = ' ' + decoded_text
# Check the partial unicode character
if chr(0xfffd) in decoded_text:
is_last = i == max_new_tokens - 1
is_stopping = token.item() == self.tokenizer.eos_token_id or shared.stop_everything
# If we are not at the end of the generation, we skip this token
if not (is_last or is_stopping):
continue
yield decoded_text
if token.item() == self.tokenizer.eos_token_id or shared.stop_everything:
break