solomonmanuelraj

Support bitsandbytes export to ONNX

7

### System Info ```shell Hi Team, Need your help to convert owl-vit model (OwlViTForObjectDetection) into onnx file. ########################################################################################## from PIL import Image from transformers import OwlViTProcessor, OwlViTForObjectDetection model_id = "google/owlvit-base-patch16"...

Hi Team, Like to use OwlViT model in a edge device. Is there a tiny model / distilled model is available. Light weight models will be helpful for edge device...

Hi Team, i use google/owlvit-base-patch32 model for zero shot object detection. To evaluate the model performance and speed, i like to use a evaluator for Zero Shot Object Detector task....

AIMET - Resnet18- 8 bit quantized Model - Need help regarding model memory size and inference time reduction with acceptable accuracy drop

3

Hi team, I am using your AIMET tool. I read in your developer blog (https://developer.qualcomm.com/blog/exploring-aimet-s-post-training-quantization-methods) the attached statement. "Table 1- Accuracies of FP32 models versus those optimized with AIMET’s CLE...

Is unsloth support PEFT Finetuning for Vision Foundation Models like OWL-ViT for Zero Shot Object Detection?

3

Hi team, Like to fine tune the vision foundation models like Owl-vit which is mainly used for zero shot object detection. Like to know whether unsloth supports this VFM Lora...

8 bit quantization and finetuning with lora is not working - receiving runtime error

4

### System Info Hi Team, when i am running the above qlora code for owl-vit model (google/owlvit-base-patch32) with below 4 bits bnbconfig , the fine tuning is taking place without...

Visualizing Grounding Dino Model Predicted Bounding Box in Voxel51 Tool ( https://voxel51.com/). Bounding Box position is changing

1

Hi Team, Thanks for your help. boxes, logits, phrases = predict( model=model, image=image, caption=TEXT_PROMPT, box_threshold=BOX_TRESHOLD, text_threshold=TEXT_TRESHOLD ) My assumption is boxes contains the [nq,4] entries. CenterX, CenterY, W, H in...

AutoGPTQ can be used to 8 bit quantize owl-vit model (google/owlvit-base-patch32) for zero shot object detection task?

2

Hi team, whether AutoGPTQ can be used to do 8 bit quantization of the owl-vit model for zero shot object detection tasks? your feedback will be helpful.

Implement ORTModelForZeroShotObjectDetection

3

### Feature request Hi team, ORT quantization tools are not available for zero shot object detection methods like owl-vit (google/owlvit-base-patch32). Creating the ORT quantization tools for zero shot object detection...

Hi Team, I am working in OWL-VIT v2 model ( google/owlv2-base-patch16-ensemble - https://huggingface.co/google/owlv2-base-patch16-ensemble/tree/main) for object detection. I want to optimize the model and reduce the memory size so that i...