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

Inifinite generation via context swapping (#71)

Browse source
This commit is contained in:
Georgi Gerganov 2023-03-25 21:36:22 +02:00
parent 03f7e33560
commit e2d490dafd
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
4 changed files with 100 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/common.h
View file

@ -21,6 +21,7 @@ struct gpt_params {
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
int32_t n_ctx = 512; // context size
int32_t n_batch = 8; // batch size for prompt processing
int32_t n_keep = 0; // number of tokens to keep from initial prompt
// sampling parameters
int32_t top_k = 40;