alihan/llama-cpp-python
1
0
Fork 0
mirror of https://github.com/abetlen/llama-cpp-python.git synced 2023-09-07 17:34:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

Added iterative search to prevent instructions from being echoed, add ignore eos, add no-mmap, fixed 1 character echo too much bug

Browse Source
This commit is contained in:
Mug
2023-04-10 16:35:38 +02:00
parent 241d608bbb
commit 0cccb41a8f
2 changed files with 35 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/low_level_api/common.py
View File

@@ -40,6 +40,7 @@ class GptParams:
instruct: bool = False
ignore_eos: bool = False
perplexity: bool = False
use_mmap: bool = True
use_mlock: bool = False
mem_test: bool = False
verbose_prompt: bool = False
@@ -110,7 +111,9 @@ def gpt_params_parse(argv = None, params: Optional[GptParams] = None):
dest="use_color"
)
parser.add_argument("--mlock", action="store_true",help="force system to keep model in RAM rather than swapping or compressing",dest="use_mlock")
parser.add_argument("--no-mmap", action="store_false",help="do not memory-map model (slower load but may reduce pageouts if not using mlock)",dest="use_mmap")
parser.add_argument("--mtest", action="store_true",help="compute maximum memory usage",dest="mem_test")
parser.add_argument("--verbose-prompt", action="store_true",help="print prompt before generation",dest="verbose_prompt")
parser.add_argument(
"-r",
"--reverse-prompt",