Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-25 17:29:22 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update models.py

Browse Source
This commit is contained in:
oobabooga 2023-03-24 19:53:20 -03:00 committed by GitHub
parent 507db0929d
commit a80aa65986
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
modules/models.py
View File

@ -44,7 +44,7 @@ def load_model(model_name):
shared.is_RWKV = model_name.lower().startswith('rwkv-')
# Default settings
if not any([shared.args.cpu, shared.args.load_in_8bit, shared.args.gptq_bits, shared.args.auto_devices, shared.args.disk, shared.args.gpu_memory is not None, shared.args.cpu_memory is not None, shared.args.deepspeed, shared.args.flexgen, shared.is_RWKV]):
if not any([shared.args.cpu, shared.args.load_in_8bit, shared.args.wbits, shared.args.auto_devices, shared.args.disk, shared.args.gpu_memory is not None, shared.args.cpu_memory is not None, shared.args.deepspeed, shared.args.flexgen, shared.is_RWKV]):
if any(size in shared.model_name.lower() for size in ('13b', '20b', '30b')):
model = AutoModelForCausalLM.from_pretrained(Path(f"models/{shared.model_name}"), device_map='auto', load_in_8bit=True)
else:
@ -95,7 +95,7 @@ def load_model(model_name):
return model, tokenizer
# Quantized model
elif shared.args.gptq_bits > 0:
elif shared.args.wbits > 0:
from modules.GPTQ_loader import load_quantized
model = load_quantized(model_name)