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

Reorder imports

Browse source
This commit is contained in:
oobabooga 2023-03-28 17:34:15 -03:00
parent 41ec682834
commit 0bec15ebcd
1 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
modules/GPTQ_loader.py
View file

@ -5,14 +5,15 @@ from pathlib import Path
import accelerate
import torch
import transformers
from transformers import AutoConfig, AutoModelForCausalLM
from transformers import AutoConfig, AutoModelForCausalLM
import modules.shared as shared
sys.path.insert(0, str(Path("repositories/GPTQ-for-LLaMa")))
import llama_inference_offload
from quant import make_quant
from modelutils import find_layers
from quant import make_quant
def _load_quant(model, checkpoint, wbits, groupsize=-1, faster_kernel=False, exclude_layers=['lm_head'], kernel_switch_threshold=128):
config = AutoConfig.from_pretrained(model)