SystemSh0cker/private-gpt
1
0
Fork 0
mirror of https://github.com/zylon-ai/private-gpt.git synced 2025-12-22 07:40:12 +01:00
Code Issues Projects Releases Packages Activity

Support n_batch to improve inference performance

Browse source
This commit is contained in:
ivan-ontruck 2023-06-11 21:33:35 +02:00
parent 52eb020256
commit ad661933cb
3 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
example.env
View file

@ -3,4 +3,5 @@ MODEL_TYPE=GPT4All
MODEL_PATH=models/ggml-gpt4all-j-v1.3-groovy.bin
EMBEDDINGS_MODEL_NAME=all-MiniLM-L6-v2
MODEL_N_CTX=1000
MODEL_N_BATCH=8
TARGET_SOURCE_CHUNKS=4