weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ptuning-v2配置

This commit is contained in:
glide-the 2023-05-18 23:19:23 +08:00
parent 55a414ecfa
commit 75cf9f9b4e
2 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/model_config.py
View File

@ -88,8 +88,6 @@ USE_PTUNING_V2 = False
# LLM running device
LLM_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
# MOSS load in 8bit
LOAD_IN_8BIT = True
VS_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "vector_store")

2
models/loader/loader.py
View File

@ -65,7 +65,7 @@ class LoaderCheckPoint:
self.tokenizer = None
self.model_dir = params.get('model_dir', '')
self.lora_dir = params.get('lora_dir', '')
self.ptuning_dir = params.get('ptuning_dir', '')
self.ptuning_dir = params.get('ptuning_dir', 'ptuning-v2')
self.cpu = params.get('cpu', False)
self.gpu_memory = params.get('gpu_memory', None)
self.cpu_memory = params.get('cpu_memory', None)