kiri VS CLIP

I'm one of the authors of Backprop, a library built for transfer learning.

I'd like to share Backprop, an open source library I've been co-authoring for the last few months.

We've also got an open-source library that makes using + finetuning these models possible in a few lines of code.

I'd like to share Backprop, a Python library I've been co-authoring for the last few months. Our goal is to make finetuning and using models as easy as possible, even without extensive ML experience.

You might get some really promising results with finetuning.

If anything, you could build writing assistance that almost automates responses.

I've been co-authoring a library that lets you finetune such models in a single line of code.

https://github.com/backprop-ai/backprop

In specific the text generation finetuning example should be what you are looking for: https://github.com/backprop-ai/backprop/blob/main/examples/F...

Hope this helps, happy to chat more about it. Pretty curious about the results.

Here's an example Jupyter Notebook for finetuning T5. Full disclosure, I work on this library myself -- but it could be helpful.

I'm working on a library that hopefully makes working with some of these a bit easier -- here's an example notebook for running text classification with the BART checkpoint, if you're interested. If you need more task-specific finetuning for text classification, that's going to be rolled out in the near future.

I'm working on a library that includes a few different ML tasks, including summarisation. It uses a pretrained version of Google's T5 transformer model, which we host on Hugging Face with some details on how it was trained.

We will also need two more libraries: OpenAI’s CLIP GitHub repo, enabling us to generate image features with the CLIP model, and the umap-learn library, which will let us apply a dimensionality reduction technique called Uniform Manifold Approximation and Projection (UMAP) to those features to visualize them in 2D:

Biggest missing feature for all these self hosted photo hosting is the lack of a real search. Being able to search for things like "beach at night" is a time saver instead of browsing through hundreds or thousands of photos. There are trained neural networks out there like https://github.com/openai/CLIP which are quite good.

In computer vision, this is known as zero-shot learning, or zero-shot prediction, because the goal is to generate predictions without explicitly being given any example predictions to learn from. With the advent of high quality multimodal models like CLIP and foundation models like Segment Anything, it is now possible to generate remarkably good zero-shot predictions for a variety of computer vision tasks, including:

(Github Repo | Most Popular Model | Paper | Project Page)

the first thing that comes to mind is CLIP: https://github.com/openai/CLIP

Whenever I’m working on semantic search applications that connect images and text, I start with a family of models known as contrastive language image pre-training (CLIP). These models are trained on image-text pairs to generate similar vector representations or embeddings for images and their captions, and dissimilar vectors when images are paired with other text strings. There are multiple CLIP-style models, including OpenCLIP and MetaCLIP, but for simplicity we’ll focus on the original CLIP model from OpenAI. No model is perfect, and at a fundamental level there is no right way to compare images and text, but CLIP certainly provides a good starting point.

in the modal card it says: pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).

Command: "C:\StabilityMatrix\Packages\stable-diffusion-webui\venv\Scripts\python.exe" -m pip install https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip --prefer-binary

CLIP might work for your needs.

pip install deepfloyd_if==1.0.2rc0 pip install xformers==0.0.16 pip install git+https://github.com/openai/CLIP.git --no-deps pip install huggingface_hub --upgrade