CogVLM

CogVLM copied to clipboard

CUDA error: an illegal memory access was encountered

3

### System Info / 系統信息 GPU: a100-80g CUDA Version: 12.1 python:3.8 pytorch:2.2.1 ### Who can help? / 谁可以帮助到您？ @1049451037 ### Information / 问题信息 - [x] The official example scripts /...

zzh-www

Some Clarification

1

### System Info / 系統信息 OS - WSL2 (Ubuntu 22.04) 32GB RAM Rtx 3090 24GB Rtx 3060 12GB Cuda - 12.1 Pytorch - 2.2.2+cu121 Transformers - 4.31.0 Python 3.10.14 ###...

deadpipe

load_in_4bit works but load_in_8bit gives error : self and mat2 must have the same dtype, but got Half and Char

3

### System Info / 系統信息 ``` Microsoft Windows [Version 10.0.19045.3996] (c) Microsoft Corporation. All rights reserved. G:\temp Local install\CogVLM\venv\Scripts>activate (venv) G:\temp Local install\CogVLM\venv\Scripts>pip freeze accelerate==0.26.1 aiofiles==23.2.1 aiohttp==3.9.3 aiosignal==1.3.1 altair==5.2.0 annotated-types==0.6.0...

FurkanGozukara

could it finetune in qlora or quant 4/8?

1

i have only a A40(48GB),how could i do to finetune the model? Althought i use lora ,i still meet the problem that "cuda out of memory". So i want to...

wyclike

### System Info / 系統信息 网页端进行图片问答，使用中文时报错  使用英文时又是正常的   ### Who can help? / 谁可以帮助到您？ _No response_ ### Information / 问题信息 - [X] The official example scripts / 官方的示例脚本...

ydygxu123

Please raise these questions in the Discussion area ｜ 这些问题请在 讨论区提出

2

以下问题不要在issue中提出，因为： 1. 这个问题是模型的上的功能缺失或者bad case 2. 官方暂时不能解决这个问题 以下问题，如果非官方代码和官方硬件上的报错，请也在Discussion中提出 #164 Mac系统环境配置 #270 微调的各种问题 #273 性能榜单复现 上述三大类问题请**不要** 在 Issue提出，否则可能会不被回复或者 直接关闭。 感谢理解 Please do not raise the following issues in the issue section because:...

zRzRzRzRzRzRzR

Inquiry on CogVLM's capacity for comprehension

2

If provided with an image containing people with labelled bounding boxes around their faces (labelled with name, race, sex, and dominant facial emotion), can CogVLM coherently describe the people as...

PhilipAmadasun

Verification of usage of roboflow to run cogVLM

5

Is this [link](https://blog.roboflow.com/how-to-deploy-cogvlm/) a legitimate source on how to use cogVLM via roboflow?

PhilipAmadasun

ValueError: model_parallel_size is inconsistent with prior configuration.We currently do not support changing model_parallel_size.

1

Traceback (most recent call last): File "/home/sagemaker-user/CogVLM/basic_demo/cli_demo_sat.py", line 162, in main() File "/home/sagemaker-user/CogVLM/basic_demo/cli_demo_sat.py", line 37, in main model, model_args = AutoModel.from_pretrained( File "/opt/conda/lib/python3.10/site-packages/sat/model/base_model.py", line 340, in from_pretrained return cls.from_pretrained_base(name, args=args,...

Hakan-Khenda

how to deny the auto created output.png

2

### System Info / 系統信息 does not matter ### Who can help? / 谁可以帮助到您？ _No response_ ### Information / 问题信息 - [X] The official example scripts / 官方的示例脚本 - [...

HarryXuancy