Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-22 08:07:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama.cpp: minor log change & lint

Browse Source
This commit is contained in:
oobabooga 2023-11-25 06:33:37 -08:00
parent 1b05832f9a
commit 68059d7c23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
modules/llamacpp_model.py
View File

@ -64,7 +64,8 @@ class LlamaCppModel:
else: else:
cache_capacity = int(shared.args.cache_capacity) cache_capacity = int(shared.args.cache_capacity)
logger.info("Cache capacity is " + str(cache_capacity) + " bytes") if cache_capacity > 0:
logger.info("Cache capacity is " + str(cache_capacity) + " bytes")
if shared.args.tensor_split is None or shared.args.tensor_split.strip() == '': if shared.args.tensor_split is None or shared.args.tensor_split.strip() == '':
tensor_split_list = None tensor_split_list = None
@ -118,9 +119,7 @@ class LlamaCppModel:
self.grammar = None self.grammar = None
def generate(self, prompt, state, callback=None): def generate(self, prompt, state, callback=None):
LogitsProcessorList = llama_cpp_lib().LogitsProcessorList LogitsProcessorList = llama_cpp_lib().LogitsProcessorList
prompt = prompt if type(prompt) is str else prompt.decode() prompt = prompt if type(prompt) is str else prompt.decode()
# Handle truncation # Handle truncation
@ -163,6 +162,7 @@ class LlamaCppModel:
for completion_chunk in completion_chunks: for completion_chunk in completion_chunks:
if shared.stop_everything: if shared.stop_everything:
break break
text = completion_chunk['choices'][0]['text'] text = completion_chunk['choices'][0]['text']
output += text output += text
if callback: if callback: