Niels Rogge's picture

Niels Rogge

nielsr

·

https://nielsrogge.github.io/

AI & ML interests

Mainly interested in diving into complex Github repos and making AI easier and more accessible to everyone

Articles

PatchTSMixer in HuggingFace

Yes, Transformers are Effective for Time Series Forecasting (+ Autoformer)

Multivariate Probabilistic Time Series Forecasting with Informer

Universal Image Segmentation with Mask2Former and OneFormer

Zero-shot image segmentation with CLIPSeg

Probabilistic Time Series Forecasting with 🤗 Transformers

Accelerating Document AI

The Annotated Diffusion Model

Fine-Tune a Semantic Segmentation Model with a Custom Dataset

Perceiver IO: a scalable, fully-attentional model that works on any modality

Organizations

nielsr's activity

New activity in llava-hf/llava-4bit 1 day ago

🚩 RuntimeError raised in Space

#5 opened 1 day ago by

New activity in llava-hf/vip-llava-7b-hf 1 day ago

The expanded size of the tensor (625) must match the existing size (129) at non-singleton dimension 3.

#5 opened 25 days ago by

New activity in llava-hf/llava-v1.6-mistral-7b-hf 2 days ago

Few Shot Example

#9 opened about 2 months ago by

How to take multiple turns conversation.

#8 opened about 2 months ago by

Is this model under license apache2.0?

#17 opened 14 days ago by

Batch processing expects images of same size

#10 opened about 1 month ago by

New activity in llava-hf/llava-v1.6-vicuna-13b-hf 2 days ago

importing error of "LlavaNextProcessor"

#1 opened about 2 months ago by

New activity in llava-hf/llava-v1.6-vicuna-13b-hf 3 days ago

Update README.md

#2 opened 3 days ago by

New activity in jozhang97/deta-swin-large 3 days ago

Upload config.json

#2 opened 5 months ago by

New activity in llava-hf/llava-1.5-7b-hf 8 days ago

convert llava-v1.5-7b to liuhaotian/llava-v1.5-7b-hf format

#26 opened 9 days ago by

New activity in google/timesfm-1.0-200m 10 days ago

Update tag

#3 opened 13 days ago by

New activity in facebook/timesformer-base-finetuned-k600 10 days ago

ImportError: cannot import name 'TimesformerFeatureExtractor' from 'transformers'

#4 opened over 1 year ago by

Deploying on Inference Endpoints API

#6 opened 7 months ago by

New activity in MCG-NJU/videomae-base-finetuned-kinetics 10 days ago

How can i obtain a feature representation for this fine-tuned model?

#2 opened over 1 year ago by

New activity in dandelin/vilt-b32-finetuned-vqa 10 days ago

Can you provide the training code for this?

#3 opened over 1 year ago by

New activity in hustvl/yolos-base 10 days ago

Does it support fine-tuning?

#3 opened 11 days ago by

New activity in llava-hf/llava-v1.6-34b-hf 13 days ago

How do you fine tune LLaVA NeXT?

#5 opened about 2 months ago by

New activity in LiheYoung/depth_anything_vitl14 13 days ago

depth-anything-large-hf vs depth_anything_vitl14

#2 opened 2 months ago by

New activity in llava-hf/llava-v1.6-mistral-7b-hf 14 days ago

Add Apache-2.0 license?

#14 opened about 1 month ago by

Update license to match upstream (Apache)

#15 opened 30 days ago by

New activity in liuhaotian/llava-v1.6-vicuna-13b 14 days ago

hugging face version coming?

#1 opened 4 months ago by

ctranslate2-4you

New activity in liuhaotian/llava-v1.6-34b 14 days ago

Fix model card metadata

#11 opened 3 months ago by

New activity in liuhaotian/llava-v1.5-7b 15 days ago

Add VLLM tag

#11 opened 3 months ago by

New activity in microsoft/table-transformer-detection 15 days ago

How to fine tune microsoft/table-transformer-detection in huggingface?

#16 opened 2 months ago by

New activity in microsoft/table-transformer-structure-recognition-v1.1-fin 15 days ago

Fine tune on own column data

#1 opened 28 days ago by

New activity in nielsr/dit-document-layout-analysis 15 days ago

Error. Maybe missing file?

#13 opened about 1 month ago by

New activity in liuhaotian/llava-v1.6-mistral-7b 15 days ago

Add VLLM tag

#4 opened 3 months ago by

New activity in llava-hf/llava-v1.6-34b-hf 15 days ago

inference with follow up questions

#10 opened about 1 month ago by

New activity in hustvl/yolos-small 15 days ago

mAP drop

#1 opened almost 2 years ago by

New activity in facebook/detr-resnet-50 15 days ago

How can I save the model in an s3 bucket

#18 opened about 2 months ago by

New activity in facebook/bart-large-mnli 17 days ago

Number of classes

#32 opened 3 months ago by

Adding `safetensors` variant of this model

#35 opened 2 months ago by

New activity in Intel/dpt-large 19 days ago

Some weights of DPTForDepthEstimation were not initialized from the model checkpoint at Intel/dpt-large

#9 opened 4 months ago by

New activity in facebook/maskformer-swin-base-coco 20 days ago

Adding `safetensors` variant of this model

#1 opened 9 months ago by

New activity in microsoft/kosmos-2-patch14-224 23 days ago

How Instal kosmos 2 on windows??

#14 opened about 1 month ago by

New activity in llava-hf/llava-1.5-7b-hf 24 days ago

How to fine-tune this model?

#23 opened 2 months ago by

Fine Tuning LLAVA for classification

#24 opened 25 days ago by

New activity in facebook/dinov2-base 24 days ago

Image size mismatch (518 vs 224)

#9 opened about 1 month ago by

New activity in google/canine-s 24 days ago

Adding `safetensors` variant of this model

#2 opened about 1 year ago by

New activity in google/canine-c 24 days ago

Adding `safetensors` variant of this model

#2 opened about 1 year ago by

New activity in microsoft/xclip-large-patch14 25 days ago

怎么使用

#1 opened 30 days ago by

New activity in Salesforce/blip2-opt-2.7b 25 days ago

Fine tuning with LORA

#33 opened about 1 month ago by

New activity in llava-hf/llava-1.5-13b-hf 25 days ago

Is the architecture for this model different from the 7b variant?

#7 opened about 1 month ago by

New activity in llava-hf/llava-v1.6-mistral-7b-hf 26 days ago

Does this support PEFT API for fine-tuning?

#16 opened 26 days ago by

New activity in IDEA-Research/grounding-dino-base 27 days ago

Fix "How to use" snippet

#3 opened about 1 month ago by

New activity in google/siglip-so400m-patch14-384 27 days ago

Probability always showing zero

#5 opened 27 days ago by

New activity in nielsr/coref-roberta-base about 1 month ago

Librarian Bot: Update Hugging Face dataset ID

#2 opened about 1 month ago by

New activity in Salesforce/blip2-opt-2.7b about 1 month ago

8bit model always returns empty string

#26 opened 3 months ago by

New activity in llava-hf/llava-v1.6-vicuna-7b-hf about 1 month ago

cannot load int4

#2 opened about 1 month ago by

New activity in llava-hf/llava-1.5-7b-hf about 1 month ago

How to have a continuous conversation

#19 opened 3 months ago by

New activity in microsoft/beit-base-patch16-224 about 1 month ago

Adding `safetensors` variant of this model

#1 opened about 1 year ago by

Move first line of bibtex to new line

#3 opened 4 months ago by

New activity in microsoft/udop-large about 1 month ago

Worse results on NER tags than LayoultLMv3

#7 opened about 1 month ago by

New activity in microsoft/table-transformer-structure-recognition about 1 month ago

Some weights of the model checkpoint at microsoft/table-transformer-structure-recognition were not used when initializing

#6 opened 7 months ago by

New activity in MIT/ast-finetuned-audioset-10-10-0.4593 about 1 month ago

How do i use it for emotion recognition?

#11 opened about 1 month ago by

New activity in llava-hf/llava-v1.6-34b-hf about 1 month ago

KeyError: "Unknown task image-text-to-text

#9 opened about 1 month ago by

New activity in llava-hf/vip-llava-7b-hf about 1 month ago

What does VIP stand for?

#1 opened 4 months ago by

Finetuning llava

#4 opened about 1 month ago by

New activity in Salesforce/blip2-opt-2.7b about 1 month ago

Adding `safetensors` variant of this model

#21 opened 5 months ago by

New activity in MIT/ast-finetuned-audioset-10-10-0.4593 about 1 month ago

Update README.md

#10 opened 2 months ago by