Update README.md

README.md

@@ -8,53 +8,49 @@ tags:
 ---
 # Model Catalogue
 
-- Describes how this repository is organized
-- Contains many boutique AI models
-- Still a work in progress
+[This repository](https://huggingface.co/agentlans) contains a collection of boutique AI models and is organized as follows:
 
-## Pretrained base models for text embedding
+## Pretrained Base Models for Text Embedding
+
+### English Models
+These models were finetuned on a subset of [Zyphra/Zyda-2](https://huggingface.co/datasets/Zyphra/Zyda-2):
 
-English models were finetuned on a subset of [Zyphra/Zyda-2](https://huggingface.co/datasets/Zyphra/Zyda-2).
 - [snowflake-arctic-embed-xs-zyda-2](https://huggingface.co/agentlans/snowflake-arctic-embed-xs-zyda-2)
 - [deberta-v3-xsmall-zyda-2](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2)
 - [deberta-v3-base-zyda-2](https://huggingface.co/agentlans/deberta-v3-base-zyda-2)
 
-Multilingual models were aligned using [agentlans/en-translations](https://huggingface.co/datasets/agentlans/en-translations).
+### Multilingual Models
+These models were aligned using [agentlans/en-translations](https://huggingface.co/datasets/agentlans/en-translations):
+
 - [multilingual-e5-small-aligned](https://huggingface.co/agentlans/multilingual-e5-small-aligned)
 - [distilbert-base-multilingual-cased-aligned](https://huggingface.co/agentlans/distilbert-base-multilingual-cased-aligned)
 
-## Text statistics models
+## Text Statistics Models
 
-- **Input:** text
-- **Output:** number
+These models take text as input and output a number.
 
-| **Base model**                | **Language** | **Quality**                                                                    | **Readability**                                                                    | **Sentiment**                                                                    |
-|:-----------------------------:|:------------:|:------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------:|
-| deberta-v3-xsmall-zyda-2      | English only | [Link](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2-quality)      | [Link](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2-readability)      | [Link](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2-sentiment)      |
-| deberta-v3-base-zyda-2        | English only | [Link](https://huggingface.co/agentlans/deberta-v3-base-zyda-2-quality)        | [Link](https://huggingface.co/agentlans/deberta-v3-base-zyda-2-readability)        | [Link](https://huggingface.co/agentlans/deberta-v3-base-zyda-2-sentiment)        |
+| Base Model | Language | Quality | Readability | Sentiment |
+|------------|----------|---------|-------------|-----------|
+| deberta-v3-xsmall-zyda-2 | English | [Link](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2-quality) | [Link](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2-readability) | [Link](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2-sentiment) |
+| deberta-v3-base-zyda-2 | English | [Link](https://huggingface.co/agentlans/deberta-v3-base-zyda-2-quality) | [Link](https://huggingface.co/agentlans/deberta-v3-base-zyda-2-readability) | [Link](https://huggingface.co/agentlans/deberta-v3-base-zyda-2-sentiment) |
 | multilingual-e5-small-aligned | Multilingual | [Link](https://huggingface.co/agentlans/multilingual-e5-small-aligned-quality) | [Link](https://huggingface.co/agentlans/multilingual-e5-small-aligned-readability) | [Link](https://huggingface.co/agentlans/multilingual-e5-small-aligned-sentiment) |
-| mdeberta-v3-base              | Multilingual | [Link](https://huggingface.co/agentlans/mdeberta-v3-base-quality)              | [Link](https://huggingface.co/agentlans/mdeberta-v3-base-readability)              | [Link](https://huggingface.co/agentlans/mdeberta-v3-base-sentiment)              |
+| mdeberta-v3-base | Multilingual | [Link](https://huggingface.co/agentlans/mdeberta-v3-base-quality) | [Link](https://huggingface.co/agentlans/mdeberta-v3-base-readability) | [Link](https://huggingface.co/agentlans/mdeberta-v3-base-sentiment) |
 
-Note: the `mdeberta-v3-base` models were trained on a previous version of the dataset, not the complete dataset
+**Note:** The `mdeberta-v3-base` models were trained on a previous version of the dataset, not the complete dataset.
 
-## Small text-to-text models
+## Small Text-to-Text Models (English Only)
 
-- **Input:** text
-- **Output:** text
+These models take text as input and produce text as output.
 
-These are English only.
-
-| **Task**           | **Model**                                                                         | **Dataset**                                                                                            |
-|:------------------:|:---------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------:|
+| Task | Model | Dataset |
+|------|-------|---------|
 | Keyword extraction | [flan-t5-small-keywords](https://huggingface.co/agentlans/flan-t5-small-keywords) | [wikipedia-paragraph-keywords](https://huggingface.co/datasets/agentlans/wikipedia-paragraph-keywords) |
-| Title generation   | [flan-t5-small-title](https://huggingface.co/agentlans/flan-t5-small-title)       | [wikipedia-paragraph-titles](https://huggingface.co/datasets/agentlans/wikipedia-paragraph-titles)     |
-
-## Natural language inference (NLI) models
+| Title generation | [flan-t5-small-title](https://huggingface.co/agentlans/flan-t5-small-title) | [wikipedia-paragraph-titles](https://huggingface.co/datasets/agentlans/wikipedia-paragraph-titles) |
+| Summarization | [text-summarization](https://huggingface.co/agentlans/text-summarization) | [wikipedia-paragraph-summaries](https://huggingface.co/datasets/agentlans/wikipedia-paragraph-summaries) |
 
-- **Input:** text
-- **Output:** label (entailment, neutral, or contradiction)
+## Natural Language Inference (NLI) Models (English Only)
 
-These are English only.
+These models take text as input and output a label (entailment, neutral, or contradiction).
 
 - [all-MiniLM-L6-v2-nli](https://huggingface.co/agentlans/all-MiniLM-L6-v2-nli)
 - [bge-small-en-v1.5-nli](https://huggingface.co/agentlans/bge-small-en-v1.5-nli)
@@ -63,4 +59,4 @@ These are English only.
 - [NoInstruct-small-Embedding-v0-nli](https://huggingface.co/agentlans/NoInstruct-small-Embedding-v0-nli)
 - [snowflake-arctic-embed-s-nli](https://huggingface.co/agentlans/snowflake-arctic-embed-s-nli)
 - [snowflake-arctic-embed-xs-nli](https://huggingface.co/agentlans/snowflake-arctic-embed-xs-nli)
-- [TinyBERT_General_4L_312D-nli](https://huggingface.co/agentlans/TinyBERT_General_4L_312D-nli)
+- [TinyBERT_General_4L_312D-nli](https://huggingface.co/agentlans/TinyBERT_General_4L_312D-nli)