Issues
- 2
The result is random
#862 opened by qfmy - 1
Evaluation of Trained SigLIP Checkpoints
#824 opened by work4cs - 0
- 10
- 1
CoCa RoBERTa Attention Map Size Issue
#864 opened by sandeepmukh - 0
Incorrect license appears on PyPI
#798 opened by alhirzel - 3
Long context CLIP
#857 opened by nicolas-dufour - 2
Issue with inference values with 'hf-hub:laion/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg'
#865 opened by dbugger29 - 1
Training speed slow
#861 opened by lezhang7 - 1
[1,512] data
#875 opened by lwtgithublwt - 1
Model coca_ViT-B-32 not found; available models = ['RN50', 'RN50-quickgelu', 'RN101', 'RN101-quickgelu', 'RN50x4', 'RN50x16', 'RN50x64', 'ViT-B-32', 'ViT-B-32-quickgelu', 'ViT-B-16', 'ViT-L-14', 'ViT-L-14-336']
#814 opened by narminGhaffari - 1
Loss isn't converging
#821 opened by zhaowenZhou - 1
How to initialize the encoder to pretrain CLIP?
#859 opened by shihuai - 1
- 1
- 0
A NotImplementedError occurred when I imported the pre-trained weights of RN50.
#846 opened by FudaMingdaXsc - 0
- 1
unlocking layer groups in open_clip/src/open_clip /timm_model.py for fine-tuning
#854 opened by mikelee-dev - 1
What is the max value for unlocked_groups in TimmModel.lock()? I am trying to fine-tune the entire vision tower
#866 opened by mikelee-dev - 0
[1,512] Data conversion
#868 opened by lwtgithublwt - 1
- 8
- 0
Load hybrid-clip in open_clip
#863 opened by code-ishwar - 2
- 10
S3 Broken Pipe Error
#845 opened by samuelstevens - 3
datasets for pretrained models
#851 opened by mikelee-dev - 1
- 1
Triton error in int8-support
#835 opened by aleablu - 1
- 1
```coca_base``` configuration does not have any ```pretrained``` arguments
#837 opened by shyammarjit - 2
How to load Clip-VIT-bigG-14 in local which has two .bin files and can not find any information how to load, thanks!!!!!!!
#841 opened by hanggun - 2
- 1
- 0
Is there someone who can share implemented script for --lock-text-unlocked-layers for "Native Clip Model"?
#830 opened by Vikho - 1
Example of launcher script with Horovod
#823 opened by guillaumeguy - 2
oscillations in the loss
#822 opened by nicolas-dufour - 1
- 0
How to reproduce the VQA results of CoCa?
#819 opened by LixDemon - 2
How does the logit_scale vary while training , i noitced that in my case it starts from the 14.28(1/0.07) and then just goes down and towards the end of the training it reaches 1
#815 opened by Akshay1-6180 - 2
- 0
What is impact on the image embedding result when the alpha channel is dropped by the converter
#801 opened by githubusersel - 1
demo code will cause memory leak
#803 opened by ltebean - 1
About width of the VIT-G model
#802 opened by OliverHuang1220 - 2
Is there any particular reason why bias term is kept as False in the projection layers
#807 opened by Akshay1-6180 - 2
Model Download fails on Mac, works on Linux
#810 opened by thomasf1 - 2
A beginner's guide to fine-tuning the CLIP model for your downstream tasks using OpenClip
#806 opened by ShuxunoO - 0
Finetuning CLIP VIT32 on COCO captions
#811 opened by MLRadfys - 0
Q-LORA for BiomedCLIP
#808 opened by Abhiram-kandiyana - 3
Issue with --lock-text Parameter in Bash Script
#805 opened by Lylinnnnn - 1
Option to load just text or image models
#799 opened by rbrtcs1