vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-16 03:49:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

explicit buffer allocation from python

Browse source
This commit is contained in:
Concedo 2023-03-20 01:18:34 +08:00
parent 356c1b87ba
commit 29054a2bee
3 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_for_kobold.py
View file

@ -48,7 +48,7 @@ def load_model(model_filename,batch_size=8,max_context_length=512,threads=4,n_pa
def generate(prompt,max_length=20,temperature=0.8,top_k=100,top_p=0.85,rep_pen=1.1,rep_pen_range=128,seed=-1,reset_state=True):
inputs = generation_inputs()
outputs = generation_outputs()
outputs = ctypes.create_unicode_buffer(ctypes.sizeof(generation_outputs))
inputs.prompt = prompt.encode("UTF-8")
inputs.max_length = max_length
inputs.temperature = temperature