Skip to content

GitLab

Commit e205548d authored by Casper Hansen's avatar Casper Hansen
Browse files

Move import up

parent 2290bdb2
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 2 deletions
awq/models/base.py
View file @ e205548d
...@@ -8,6 +8,7 @@ from typing import List, Union ...@@ -8,6 +8,7 @@ from typing import List, Union
from safetensors.torch import save_file from safetensors.torch import save_file
from awq.modules.act import ScaledActivation from awq.modules.act import ScaledActivation
from huggingface_hub import snapshot_download from huggingface_hub import snapshot_download
from awq.quantize.quantizer import AwqQuantizer
from awq.utils.utils import simple_dispatch_model from awq.utils.utils import simple_dispatch_model
from transformers.modeling_utils import shard_checkpoint from transformers.modeling_utils import shard_checkpoint
from awq.modules.linear import WQLinear_GEMM, WQLinear_GEMV from awq.modules.linear import WQLinear_GEMM, WQLinear_GEMV
...@@ -41,8 +42,6 @@ class BaseAWQForCausalLM(nn.Module): ...@@ -41,8 +42,6 @@ class BaseAWQForCausalLM(nn.Module):
self.quant_config = quant_config self.quant_config = quant_config
quant_config["version"] = "GEMM" if 'version' not in quant_config.keys() else quant_config["version"] quant_config["version"] = "GEMM" if 'version' not in quant_config.keys() else quant_config["version"]
from awq.quantize.quantizer import AwqQuantizer
quantizer = AwqQuantizer( quantizer = AwqQuantizer(
self, self.model, tokenizer, quant_config["w_bit"], quant_config["q_group_size"], self, self.model, tokenizer, quant_config["w_bit"], quant_config["q_group_size"],
quant_config["version"], calib_data, split, text_column quant_config["version"], calib_data, split, text_column
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment