Adding `safetensors` variant of this model (#7)

- Adding `safetensors` variant of this model (6e4ddb8f8df76f08859d9022a45085133895bce6)


Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>

README.md

@@ -8,11 +8,15 @@ tags:
 library_name: transformers
 language:
 - en
+widget:
+  - src: https://cdn-images.farfetch-contents.com/19/76/05/56/19760556_44221665_1000.jpg
+    candidate_labels: black shoe, red shoe, a cat
+    example_title: Black Shoe
 ---
 
 [![Youtube Video](https://img.shields.io/badge/youtube-video-red)](https://www.youtube.com/watch?v=uqRSc-KSA1Y)
 [![HuggingFace Model](https://img.shields.io/badge/HF%20Model-Weights-yellow)](https://huggingface.co/patrickjohncyh/fashion-clip)
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1n--D_CBPEEO7fCcebHIxbbY4dr5incaD?usp=sharing)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1Z1hAxBnWjF76bEi9KQ6CMBBEmI_FVDrW?usp=sharing)
 [![Medium Blog Post](https://raw.githubusercontent.com/aleen42/badges/master/src/medium.svg)](https://towardsdatascience.com/teaching-clip-some-fashion-3005ac3fdcc3)
 
 # Model Card: Fashion CLIP
@@ -21,6 +25,18 @@ Disclaimer: The model card adapts the model card from [here](https://huggingface
 
 ## Model Details
 
+UPDATE (10/03/23): We have updated the model! We found that [laion/CLIP-ViT-B-32-laion2B-s34B-b79K](https://huggingface.co/laion/CLIP-ViT-B-32-laion2B-s34B-b79K) checkpoint (thanks [Bin](https://www.linkedin.com/in/bin-duan-56205310/)!) worked better than original OpenAI CLIP on Fashion. We thus fine-tune a newer (and better!) version of FashionCLIP (henceforth FashionCLIP 2.0), while keeping the architecture the same. We postulate that the perofrmance gains afforded by `laion/CLIP-ViT-B-32-laion2B-s34B-b79K` are due to the increased training data (5x OpenAI CLIP data). Our [thesis](https://www.nature.com/articles/s41598-022-23052-9), however, remains the same -- fine-tuning `laion/CLIP` on our fashion dataset improved zero-shot perofrmance across our benchmarks. See the below table comparing weighted macro F1 score across models.
+`
+
+| Model             | FMNIST        | KAGL          | DEEP          | 
+| -------------     | ------------- | ------------- | ------------- |
+| OpenAI CLIP       | 0.66          | 0.63          | 0.45          |
+| FashionCLIP       | 0.74          | 0.67          | 0.48          |
+| Laion CLIP        | 0.78          | 0.71          | 0.58          |
+| FashionCLIP 2.0   | __0.83__          | __0.73__          | __0.62__          |
+
+---
+
 FashionCLIP is a CLIP-based model developed to produce general product representations for fashion concepts. Leveraging the pre-trained checkpoint (ViT-B/32) released by [OpenAI](https://github.com/openai/CLIP), we train FashionCLIP on a large, high-quality novel fashion dataset to study whether domain specific fine-tuning of CLIP-like models is sufficient to produce product representations that are zero-shot transferable to entirely new datasets and tassks. FashionCLIP was not developed for model deplyoment - to do so, researchers will first need to carefully study their capabilities in relation to the specific context they’re being deployed within.
 
 ### Model Date