mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Rename --llama-bits to --gptq-bits

Browse source
This commit is contained in:
oobabooga 2023-03-12 11:19:07 -03:00
parent fed3617f07
commit 65dda28c9d
3 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/models.py
View file

@ -42,7 +42,7 @@ 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.load_in_4bit, shared.args.llama_bits > 0, 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.load_in_4bit, shared.args.gptq_bits > 0, 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:
@ -88,7 +88,7 @@ def load_model(model_name):
return model, tokenizer
# 4-bit LLaMA
elif shared.args.llama_bits > 0 or shared.args.load_in_4bit:
elif shared.args.gptq_bits > 0 or shared.args.load_in_4bit:
from modules.quantized_LLaMA import load_quantized_LLaMA
model = load_quantized_LLaMA(model_name)