vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Detect multi-byte responses and wait

Browse source
This commit is contained in:
Mug 2023-04-28 12:50:30 +02:00 • committed by Don Mahurin
parent 36b3494332
commit 441d30811a
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/low_level_api_chat_cpp.py
View file

@ -96,7 +96,7 @@ specified) expect poor results""", file=sys.stderr)
print(file=sys.stderr) print(file=sys.stderr)
print(f"system_info: n_threads = {self.params.n_threads} / {cpu_count()} \ print(f"system_info: n_threads = {self.params.n_threads} / {cpu_count()} \
| {llama_cpp.llama_print_system_info().decode('utf8', errors='ignore')}", file=sys.stderr) | {llama_cpp.llama_print_system_info().decode('utf8')}", file=sys.stderr)
# determine the required inference memory per token: # determine the required inference memory per token:
if (self.params.mem_test): if (self.params.mem_test):