dagshub/open-source-ml-models

This repository holds open-source machine learning models for various domains ready to download and use

What is DagsHub?

DagsHub is a platform where machine learning and data science teams can build, manage, and collaborate on their projects. With DagsHub you can:

1. Version code, data, and models in one place. Use the free provided DagsHub storage or connect it to your cloud storage
2. Track Experiments using Git, DVC or MLflow, to provide a fully reproducible environment
3. Visualize pipelines, data, and notebooks in and interactive, diff-able, and dynamic way
4. Label your data directly on the platform using Label Studio
5. Share your work with your team members
6. Stream and upload your data in an intuitive and easy way, while preserving versioning and structure.

DagsHub is built firmly around open, standard formats for your project. In particular:

• Git
• DVC
• MLflow
• Label Studio
• Standard data formats like YAML, JSON, CSV

Therefore, you can work with DagsHub regardless of your chosen programming language or frameworks.

DagsHub Client API & CLI

This client library is meant to help you get started quickly with DagsHub. It is made up of Experiment tracking and Direct Data Access (DDA), a component to let you stream and upload your data.

For more details on the different functions of the client, check out the docs segments:

1. Installation & Setup
2. Data Streaming
3. Data Upload
4. Experiment Tracking
   1. Autologging
5. Data Engine

Some functionality is supported only in Python.

To read about some of the awesome use cases for Direct Data Access, check out the relevant doc page.

Installation

pip install dagshub

Direct Data Access (DDA) functionality requires authentication, which you can easily do by running the following command in your terminal:

dagshub login

Quickstart for Data Streaming

The easiest way to start using DagsHub is via the Python Hooks method. To do this:

1. Your DagsHub project,
2. Copy the following 2 lines of code into your Python code which accesses your data:

   from dagshub.streaming import install_hooks
   install_hooks()

3. That’s it! You now have streaming access to all your project files.

🤩 Check out this colab to see an example of this Data Streaming work end to end:

Next Steps

You can dive into the expanded documentation, to learn more about data streaming, data upload and experiment tracking with DagsHub

---

Analytics

To improve your experience, we collect analytics on client usage. If you want to disable analytics collection, set the DAGSHUB_DISABLE_ANALYTICS environment variable to any value.

Made with 🐶 by DagsHub.

open-source-ml-models's Issues

Claim: bert-base-cased HuggingFace Model

This issue aims to add the following ML Model to DagsHub.

BERT base model (cased)

Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is case-sensitive: it makes a difference between english and English.

HuggingFace Link: https://huggingface.co/bert-base-cased

Claim: nlpconnect/vit-gpt2-image-captioning HuggingFace Model

This issue aims to add the following ML Model to DagsHub.

nlpconnect/vit-gpt2-image-captioning

This is an image captioning model trained by @ydshieh in Flax

HuggingFace Link: https://huggingface.co/nlpconnect/vit-gpt2-image-captioning

Claim: magorshunov/layoutlm-invoices HuggingFace Model

This issue aims to add the following ML Model to DagsHub.

magorshunov/layoutlm-invoices

This is a fine-tuned version of the multi-modal LayoutLM model for the task of question answering on invoices and other documents. It has been fine-tuned on a proprietary dataset of invoices as well as both SQuAD2.0 and DocVQA for general comprehension.

HuggingFace Link: https://huggingface.co/magorshunov/layoutlm-invoices

Claim: dandelin/vilt-b32-finetuned-vqa HuggingFace Model

This issue aims to add the following ML model to DagsHub

dandelin/vilt-b32-finetuned-vqa

Vision-and-Language Transformer (ViLT) model fine-tuned on VQAv2. It was introduced in the paper ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision by Kim et al. and first released in this repository.

HuggingFace Link: https://huggingface.co/dandelin/vilt-b32-finetuned-vqa

Claim: facebook/bart-large-cnn HuggingFace Model

This issue aims to add the following ML Model to DagsHub.

facebook/bart-large-cnn

BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.

BART is particularly effective when fine-tuned for text generation (e.g. summarization, translation) but also works well for comprehension tasks (e.g. text classification, question answering). This particular checkpoint has been fine-tuned on CNN Daily Mail, a large collection of text-summary pairs.

HuggignFace Link: https://huggingface.co/facebook/bart-large-cnn

Claim: Salesforce/blip-image-captioning-large HuggingFace Model

This issue aims to add the following ML model to DagsHub.

Salesforce/blip-image-captioning-large

This model is used for conditional and un-conditional image captioning.

HuggingFace Link: https://huggingface.co/Salesforce/blip-image-captioning-large

I can contribute siamese network to this repo

Siamese network for face detection with proper readme file
Hope you will assign me the issue.

Claim: damo-vilab/text-to-video-ms-1.7b HuggingFace Model

This issue aims to add the following ML Model to DagsHub.

damo-vilab/text-to-video-ms-1.7b

This model is based on a multi-stage text-to-video generation diffusion model, which inputs a description text and returns a video that matches the text description. Only English input is supported.

HuggingFace Link: https://huggingface.co/damo-vilab/text-to-video-ms-1.7b

Claim: stabilityai/stable-diffusion-xl-base-1.0 HuggingFace Model

This issue aims to add the following ML Model to DagsHub

stabilityai/stable-diffusion-xl-base-1.0

SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model is used to generate (noisy) latents, which are then further processed with a refinement model available here specialized for the final denoising steps.

HuggingFace Link: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0

Claim: fxmarty/tiny-doc-qa-vision-encoder-decoder HuggingFace Model

This issue aims to add the following ML Model to DagsHub.

fxmarty/tiny-doc-qa-vision-encoder-decoder

This is a model that can be used for document question answering.

HuggingFace Link: https://huggingface.co/fxmarty/tiny-doc-qa-vision-encoder-decoder

Claim: distilbert-base-uncased-finetuned-sst-2-english HuggingFace Model

This issue aims to add the following ML Model to DagsHub.

distilbert-base-uncased-finetuned-sst-2-english

This model is a fine-tune checkpoint of DistilBERT-base-uncased, fine-tuned on SST-2. This model reaches an accuracy of 91.3 on the dev set (for comparison, Bert bert-base-uncased version reaches an accuracy of 92.7).

This model can be used for topic classification. You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task.

HuggingFace Link: https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english

Claim : impira/layoutlm-document-qa HuggignFace Model

This issue aims to add the following ML Model to DagsHub.

impira/layoutlm-document-qa

This is a fine-tuned version of the multi-modal LayoutLM model for the task of question answering on documents. It has been fine-tuned using both the SQuAD2.0 and DocVQA datasets.

HuggingFace Link: https://huggingface.co/impira/layoutlm-document-qa

Claim: google/pix2struct-docvqa-base HuggingFace Model

This issue aims to add the following ML Model to DagsHub.

google/pix2struct-docvqa-base

Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering.

HuggingFace Link: https://huggingface.co/google/pix2struct-docvqa-base