deepgeek/MiniCPM-o
2
0
Fork 0
mirror of https://github.com/OpenBMB/MiniCPM-V.git synced 2026-02-05 18:29:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

修改了一下使用cuda的断言

Browse Source
This commit is contained in:
root
2024-07-30 14:44:56 +08:00
parent e760f96974
commit e88f8283a9
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
quantize/bnb_quantize.py
View File

@@ -18,11 +18,14 @@ import torch
import GPUtil import GPUtil
import os import os
assert torch.cuda.is_available(),"CUDA is not available, but this code requires a GPU."
device = 'cuda' # Select GPU to use
model_path = '/root/ld/ld_model_pretrained/MiniCPM-Llama3-V-2_5' # Model download path model_path = '/root/ld/ld_model_pretrained/MiniCPM-Llama3-V-2_5' # Model download path
device = 'cuda' # Select GPU if available, otherwise CPU
save_path = '/root/ld/ld_model_pretrain/MiniCPM-Llama3-V-2_5_int4' # Quantized model save path save_path = '/root/ld/ld_model_pretrain/MiniCPM-Llama3-V-2_5_int4' # Quantized model save path
image_path = './assets/airplane.jpeg' image_path = './assets/airplane.jpeg'
# Create a configuration object to specify quantization parameters # Create a configuration object to specify quantization parameters
quantization_config = BitsAndBytesConfig( quantization_config = BitsAndBytesConfig(
load_in_4bit=True, # Whether to perform 4-bit quantization load_in_4bit=True, # Whether to perform 4-bit quantization