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

Fix the missing Chinese character bug (#2497)

Browse Source
This commit is contained in:
GralchemOz 2023-06-03 00:45:41 +08:00 committed by GitHub
parent 28198bc15c
commit f7b07c4705
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
modules/RWKV.py
View File

@ -87,7 +87,9 @@ class RWKVModel:
while len(tokens) > 0: while len(tokens) > 0:
out, state = self.model.forward(tokens[:args.chunk_len], state) out, state = self.model.forward(tokens[:args.chunk_len], state)
tokens = tokens[args.chunk_len:] tokens = tokens[args.chunk_len:]
if i == 0:
begin_token= len(all_tokens)
last_token_posi=begin_token
# cache the model state after scanning the context # cache the model state after scanning the context
# we don't cache the state after processing our own generated tokens because # we don't cache the state after processing our own generated tokens because
# the output string might be post-processed arbitrarily. Therefore, what's fed into the model # the output string might be post-processed arbitrarily. Therefore, what's fed into the model
@ -116,13 +118,13 @@ class RWKVModel:
occurrence[token] += 1 occurrence[token] += 1
# output # output
tmp = self.pipeline.decode([token]) tmp = self.pipeline.decode(all_tokens[last_token_posi:])
if '\ufffd' not in tmp: # is valid utf-8 string? if '\ufffd' not in tmp: # is valid utf-8 string?
if callback: if callback:
callback(tmp) callback(tmp)
out_str += tmp out_str += tmp
last_token_posi = begin_token + i + 1
return out_str return out_str