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

Reduce chatLLaMa context size to 2048

Browse source 
Ref d7def1a752
This commit is contained in:
Jean-Christophe Hoelt 2023-03-19 14:11:05 +02:00
parent b6bcd016b1
commit b8c383a9b9
No known key found for this signature in database
GPG key ID: 838AF264602A1B37
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/chatLLaMa
View file

@ -13,7 +13,7 @@ N_PREDICTS="${N_PREDICTS:-1024}"
# Note: you can also override the generation options by specifying them on the command line:
# For example, override the context size by doing: ./chatLLaMa --ctx_size 2048
GEN_OPTIONS="${GEN_OPTIONS:---ctx_size 4096 --temp 0.7 --top_k 40 --top_p 0.5 --repeat_last_n 256 --repeat_penalty 1.17647}"
GEN_OPTIONS="${GEN_OPTIONS:---ctx_size 2048 --temp 0.7 --top_k 40 --top_p 0.5 --repeat_last_n 256 --repeat_penalty 1.17647}"
# shellcheck disable=SC2086 # Intended splitting of GEN_OPTIONS
./main $GEN_OPTIONS \