Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / NielsRogge/Transformers-Tutorials issues and pull requests
#464 - KeyError: 'pixel_values' Linear probing with ImageGPT.ipynb
Issue -
State: open - Opened by ArtificialZeng 6 days ago
#463 - Inconsistent Bounding Box Results with OWLv2 Image-Guided Detection
Issue -
State: open - Opened by HuzefaAnver 13 days ago
#462 - paligemma tokens not added
Issue -
State: open - Opened by stellanhaglund 15 days ago
#461 - LLaVa-NeXT/Fine_tune_LLaVaNeXT_on_a_custom_dataset_(with_PyTorch_Lightning).ipynb fails at training
Issue -
State: open - Opened by 7AtAri 20 days ago
#460 - Generate text for all images
Issue -
State: open - Opened by hliu56 about 1 month ago
#459 - fix type to comply with albumentation, fix shape in loss calculation
Pull Request -
State: open - Opened by zinccat about 1 month ago
- 1 comment
#458 - Add LLaVA-NeXT-Video
Pull Request -
State: closed - Opened by zucchini-nlp about 2 months ago
- 3 comments
#457 - Supervised fine tuning (SFT) of an LLM using HuggingFace, no availabel files for LoRA
Issue -
State: open - Opened by vietvo89 about 2 months ago
#456 - Why are instructions not masked when performing SFT on large multimodal models?
Issue -
State: closed - Opened by shijian2001 about 2 months ago
- 3 comments
#455 - LLaVa-NeXT fine-tuning
Pull Request -
State: closed - Opened by zucchini-nlp about 2 months ago
- 2 comments
#454 - TUTORIAL ON AGENTS AND TOOLS
Issue -
State: open - Opened by spydaz 2 months ago
#453 - Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length.
Issue -
State: open - Opened by code-amalps 2 months ago
- 1 comment
#452 - Failed to clone Fine_tune_PaliGemma_for_image_>JSON.ipynb
Issue -
State: open - Opened by MRNOBODY-ZST 2 months ago
#451 - How to prepare datasets for docvqa to fine-tune donut
Issue -
State: open - Opened by Dineshkumar-Anandan-ZS0367 2 months ago
#450 - Img2Txt model fine-tuning with huge captions
Issue -
State: open - Opened by AeroDEmi 2 months ago
#449 - Fine_tune_PaliGemma_for_image_>JSON.ipynb
Issue -
State: open - Opened by hitchhiker3010 2 months ago
#448 - trying to access VisionEncoderDecoderModel DONUT encoder intermediate layers
Issue -
State: open - Opened by AbdulDD 3 months ago
#447 - Fine-tune LayoutXLM on XFUND (relation extraction):Fine-tune LayoutXLM on XFUND (relation extraction)
Issue -
State: open - Opened by Still-FanTasy 3 months ago
#446 - Can the TrOCR be fine-tuned for entire page instead of a sentence or a single line
Issue -
State: open - Opened by AtharvBhujade 3 months ago
#445 - Mask2Former-model: AttributeError: 'list' object has no attribute 'shape' on inference
Issue -
State: closed - Opened by beschmitt 3 months ago
#444 - how to build a LiLT RobertaXML model with LayoutLMv3 tokenizer
Issue -
State: open - Opened by MattBlue92 3 months ago
#443 - Automatic-Mask-Generation use finetuning model on SAM.
Issue -
State: open - Opened by unmo 3 months ago
- 1 comment
#442 - Pali Gemma model for snippet extractions from an image
Issue -
State: open - Opened by AGRocky 3 months ago
#441 - Why do you need custom Features?
Issue -
State: closed - Opened by gordon-lim 3 months ago
- 2 comments
#440 - IndexError: index out of range in self
Issue -
State: open - Opened by Soham07081 3 months ago
#439 - Dinov2 HF based notebooks with multi scale and Mask2former
Issue -
State: open - Opened by ayushnangia 3 months ago
- 1 comment
#438 - Linear probing with ImageGPT: Attribute Error pixel_values
Issue -
State: open - Opened by AasherH 3 months ago
#437 - Fine_tune_PaliGemma_for_image_>JSON.ipynb CUDA out of memory
Issue -
State: open - Opened by ttkrpink 3 months ago
#436 - Inference for Idefics2 after lora fine tuning
Issue -
State: open - Opened by jackiexue1993 3 months ago
- 1 comment
#435 - Fine_tune_PaliGemma_for_image_>JSON.ipynb: Kernel crashes
Issue -
State: open - Opened by lhericourt 3 months ago
#434 - Shape mismatch issue in Fine-tuing of Idefics 2 Tutorial
Issue -
State: closed - Opened by chang-changiti 3 months ago
- 1 comment
#433 - Enforce JSON structure with PaliGemma/Donut
Issue -
State: closed - Opened by MayStepanyan 3 months ago
- 5 comments
#432 - Tensor size mismatch for table detection in PDF
Issue -
State: open - Opened by sanakashgouli 3 months ago
#431 - Handling Multiple Images PDFs in a Notebook and Seeking Guidance on Code Modification
Issue -
State: closed - Opened by AnasLahmar 4 months ago
- 5 comments
#430 - Confidence score for paligemma
Issue -
State: open - Opened by himasai9712 4 months ago
- 7 comments
#429 - 🟢 Image to JSON Conversion Instead of ❌ PDF to JSON
Issue -
State: closed - Opened by AnasLahmar 4 months ago
- 2 comments
#428 - Question about LoRA Target in Fine-tuning of Idefics2
Issue -
State: open - Opened by kash203 4 months ago
- 1 comment
#427 - Add notebooks for VideoLLaVa
Pull Request -
State: closed - Opened by zucchini-nlp 4 months ago
- 1 comment
#426 - Fine Tuning CodeT5p-770m model for text-to-code
Issue -
State: open - Opened by SerenaDeAntoni 4 months ago
- 1 comment
#425 - DETA Swin Large: Input image size (800*800) doesn't match model (224*224).
Issue -
State: open - Opened by Nayal17 4 months ago
#424 - Fine-tuning BERT
Issue -
State: open - Opened by saakolch 4 months ago
#423 - TrOCR small for license plate
Issue -
State: open - Opened by SwEngine 4 months ago
#422 - - [x] https://github.com/NielsRogge/Transformers-Tutorials/issues/421#issue-2287902399
Issue -
State: open - Opened by zoevailanu0 4 months ago
#421 - Adding Inference Pipeline for Table-Transformer
Issue -
State: open - Opened by rudra0713 4 months ago
- 1 comment
#420 - UDOP - Fine tuning with bad metrics
Issue -
State: open - Opened by arvisioncode 5 months ago
- 2 comments
#419 - BitsAndBytesConfig cannot resolve torch.bfloat16
Pull Request -
State: open - Opened by qiisziilbash 5 months ago
- 1 comment
#418 - "Unused or unrecognized kwargs: padding" error when running notebook example
Issue -
State: open - Opened by jferments 5 months ago
#417 - Table transformer demo not handling empty cells
Issue -
State: open - Opened by billou2k 5 months ago
#416 - SAM Instance segmentation Finetuning output mask with instance lablel
Issue -
State: open - Opened by Abonia1 5 months ago
#415 - Mask2Former panoptic fine-tune
Issue -
State: open - Opened by strangeTany 5 months ago
- 3 comments
#414 - can't login to push hub model
Issue -
State: open - Opened by khairulu 5 months ago
#413 - [Finetuning OneFormer] How to use multiple GPUs
Issue -
State: open - Opened by EricLe-dev 5 months ago
#412 - Fine tune TrOCR on IAM Handwriting Database using Seq2SeqTrainer
Issue -
State: open - Opened by johnlockejrr 5 months ago
- 13 comments
#411 - Grounded sam example
Pull Request -
State: closed - Opened by EduardoPach 5 months ago
- 2 comments
#410 - Grounding Dino - Multiple Class
Issue -
State: closed - Opened by Hangsiin 5 months ago
- 3 comments
#409 - Huge negative loss while fine-tuning SAM
Issue -
State: closed - Opened by martintomov 5 months ago
- 2 comments
#408 - True Inference with Layoutlmv3
Issue -
State: open - Opened by Monta79 5 months ago
- 2 comments
#407 - [Bug] Owlv2 Zero-shot object detection
Issue -
State: open - Opened by nisyad-ms 5 months ago
#406 - UDOP - Is it possible to get several bboxes from one single input ?
Issue -
State: open - Opened by polodealvarado 6 months ago
#405 - How can we Fine Tune Pix2StruCt for DocVQA task?
Issue -
State: open - Opened by AbdulDD 6 months ago
#404 - UDOP - How to change UdopToknizer to another tokenizer that supports CJK languages?
Issue -
State: open - Opened by pascona 6 months ago
- 1 comment
#403 - Table transformer crop issue
Issue -
State: open - Opened by tzktz 6 months ago
#402 - LayoutLM prediction with confidence score?
Issue -
State: open - Opened by nk-alex 6 months ago
- 1 comment
#401 - UDOP FUNSD , not able to perform Inference
Issue -
State: open - Opened by fathyshalaby 6 months ago
- 2 comments
#400 - fine-tune the model
Issue -
State: open - Opened by Siddhijain16 6 months ago
#399 - UDOP Document Generation & Editing
Issue -
State: closed - Opened by boris-lok-pentadoc 6 months ago
- 2 comments
#398 - Donut fine tuning using Huggingface accelerate
Issue -
State: open - Opened by SNavgale 6 months ago
#397 - UDOP different models
Issue -
State: open - Opened by arvisioncode 7 months ago
- 2 comments
#396 - UDOP Demo notebooks
Issue -
State: open - Opened by AurelienVaudois 7 months ago
- 2 comments
#394 - UDOP for Information Extraction.
Issue -
State: closed - Opened by Akhilesh64 7 months ago
- 2 comments
#375 - Suggestion for better way to apply OCR on table cells
Issue -
State: open - Opened by abielr 9 months ago
- 1 comment
#369 - BUG: LayoutLMv3 finetuning on FUNSD Notebook; data preprocessing features
Issue -
State: closed - Opened by Davo00 10 months ago
- 4 comments
#362 - TrOCR decoder_start_token should be `eos` instead of `cls`.
Pull Request -
State: open - Opened by thariq-nugrohotomo 11 months ago
- 1 comment
#359 - Fix #358: Evaluate on test instead of validation dataset
Pull Request -
State: open - Opened by PierreMesure 11 months ago
- 2 comments
#355 - Can `VisionEncoderDecoderModel.generate()` work with batched data?
Issue -
State: open - Opened by plamb-viso 11 months ago
- 2 comments
#354 - Clarification on the Nougat Transformers
Issue -
State: open - Opened by Dipankar1997161 11 months ago
- 4 comments
#337 - Dinov2 semantic segmentation error after the first epoch
Issue -
State: open - Opened by ogencoglu about 1 year ago
- 3 comments
#333 - Donut-How to use a tokenizer with multiple language support
Issue -
State: open - Opened by Theerath about 1 year ago
- 2 comments
#331 - Fine tuning SAM with multiple bounding boxes
Issue -
State: closed - Opened by mohdsaqibxa about 1 year ago
- 9 comments
#324 - Inference on fine tuned LayoutLMv3 model
Issue -
State: open - Opened by nn-Nikita over 1 year ago
- 5 comments
#304 - Perform Relation Extraction by LayoutLMV2 instead of LayoutXLM
Issue -
State: open - Opened by yang0369 over 1 year ago
- 2 comments
#298 - update LR
Pull Request -
State: open - Opened by cdreetz over 1 year ago
- 1 comment
#296 - How to train Mask2Former from a COCO json custom dataset?
Issue -
State: open - Opened by Robotatron over 1 year ago
- 9 comments
#288 - Update README.md
Pull Request -
State: open - Opened by eltociear over 1 year ago
#285 - Obtaining pixel_values and task_inputs to pass to OneFormer's forward() function for fine-tuning on instance segmentation
Issue -
State: open - Opened by nikolaydyankov over 1 year ago
- 4 comments
#283 - Donut model size beyond 768*2 max_length
Issue -
State: open - Opened by nik13 over 1 year ago
- 3 comments
#280 - Update Fine_tune_SegFormer_on_custom_dataset_[RUGD].ipynb
Pull Request -
State: open - Opened by aquib1011 over 1 year ago
- 1 comment
#276 - Donut inference is extremely slow when loading from checkpoint
Issue -
State: open - Opened by MS1908 over 1 year ago
- 1 comment
#253 - How to change LayoutLMv3 to a LayoutLMv3 XLM (i.e. LayoutXLM-like model)
Issue -
State: open - Opened by piegu over 1 year ago
- 6 comments
#243 - Train Mask2Former on custom dataset
Issue -
State: closed - Opened by lombardata over 1 year ago
- 40 comments
#236 - Inference with nielsr/lilt-xlm-roberta-base
Issue -
State: open - Opened by piegu over 1 year ago
- 13 comments
#219 - json annotations translation (IOB to form)
Issue -
State: open - Opened by iwaqas almost 2 years ago
- 7 comments
#200 - streamlit app using Table Transformer and OCR
Pull Request -
State: open - Opened by salman-moh almost 2 years ago
- 5 comments
#187 - layoutlmv3, true inference, return corresponding text for detected labels
Issue -
State: closed - Opened by aditya11ad almost 2 years ago
- 7 comments
#175 - Fine tuning DiT for object detection task
Issue -
State: open - Opened by deshwalmahesh about 2 years ago
- 5 comments
#167 - Update Custom_Named_Entity_Recognition_with_BERT.ipynb
Pull Request -
State: open - Opened by sufianj about 2 years ago
- 1 comment
#144 - Need help in key value pair extraction.
Issue -
State: closed - Opened by Laxmi530 about 2 years ago
- 15 comments
#128 - True_inference_with_LayoutLMv2ForTokenClassification, add support for custom OCR
Pull Request -
State: open - Opened by amtam0 over 2 years ago
- 1 comment
#124 - TrOCR image resizing
Issue -
State: open - Opened by siljuovix over 2 years ago
- 3 comments
#123 - Train layoutlmv3 with custom dataset by loading from local directory
Issue -
State: closed - Opened by deepanshudashora over 2 years ago
- 25 comments