edugp commited on
Commit
de5d267
1 Parent(s): 04899df

Update README to link to BERTIN

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -7,8 +7,9 @@ tags:
7
  - vit
8
  ---
9
  # CLIP-Spanish
10
- CLIP Spanish is a CLIP-like Model for Spanish. It is composed of a RoBERTa-base language encoder and a ViT-B/32 image encoder using [Flax](https://github.com/google/flax), including training scripts (see training.md).
11
  This is part of the [Flax/Jax Community Week](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104), organised by [HuggingFace](https://huggingface.co/) and TPU usage sponsored by Google.
 
12
  ## Spanish WIT
13
  We used a subset of 141,230 Spanish captions from the [WIT dataset](https://github.com/google-research-datasets/wit) for training.
14
 
@@ -16,6 +17,7 @@ We used a subset of 141,230 Spanish captions from the [WIT dataset](https://gith
16
  - Eduardo González Ponferrada ([edugp](https://huggingface.co/edugp))
17
  - Manu Romero ([mrm8488](https://huggingface.co/))
18
  - María Grandury ([mariagrandury](https://huggingface.co/))
 
19
  ## Useful links
20
  - [Community Week timeline](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104#summary-timeline-calendar-6)
21
  - [Community Week README](https://github.com/huggingface/transformers/blob/master/examples/research_projects/jax-projects/README.md)
 
7
  - vit
8
  ---
9
  # CLIP-Spanish
10
+ CLIP Spanish is a CLIP-like model for Spanish language. It is composed of [BERTIN](https://huggingface.co/bertin-project/bertin-roberta-base-spanish) as a language encoder and the ViT-B/32 image encoder from [CLIP](https://huggingface.co/openai/clip-vit-base-patch32). The model is implemented in [Flax](https://github.com/google/flax), including training scripts (see `training.md`).
11
  This is part of the [Flax/Jax Community Week](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104), organised by [HuggingFace](https://huggingface.co/) and TPU usage sponsored by Google.
12
+
13
  ## Spanish WIT
14
  We used a subset of 141,230 Spanish captions from the [WIT dataset](https://github.com/google-research-datasets/wit) for training.
15
 
 
17
  - Eduardo González Ponferrada ([edugp](https://huggingface.co/edugp))
18
  - Manu Romero ([mrm8488](https://huggingface.co/))
19
  - María Grandury ([mariagrandury](https://huggingface.co/))
20
+
21
  ## Useful links
22
  - [Community Week timeline](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104#summary-timeline-calendar-6)
23
  - [Community Week README](https://github.com/huggingface/transformers/blob/master/examples/research_projects/jax-projects/README.md)