Trent commited on
Commit
e01d8a9
·
1 Parent(s): 113ad6b

Contributions

Browse files
Files changed (1) hide show
  1. app.py +6 -6
app.py CHANGED
@@ -18,7 +18,7 @@ Hi! This is the demo for the [flax sentence embeddings](https://huggingface.co/f
18
  We trained three general-purpose flax-sentence-embeddings models: a **distilroberta base**, a **mpnet base** and a **minilm-l6**.
19
  The models were trained on a dataset comprising of [1 Billion+ training corpus](https://huggingface.co/flax-sentence-embeddings/all_datasets_v4_MiniLM-L6#training-data) with the v3 setup.
20
 
21
- In addition, we trained [20 models](https://huggingface.co/flax-sentence-embeddings) focused on general-purpose, QuestionAnswering and Code search and achieved SOTA on multiple benchmarks.
22
  We also uploaded [8 datasets](https://huggingface.co/flax-sentence-embeddings) specialized for Question Answering, Sentence-Similiarity and Gender Evaluation.
23
  You can view our models and datasets [here](https://huggingface.co/flax-sentence-embeddings).
24
 
@@ -29,12 +29,12 @@ You can view our models and datasets [here](https://huggingface.co/flax-sentence
29
 
30
  ## Contributions
31
 
32
- - 20 performant Sentence Embedding models that can be utilized for Sentence Simliarity / Asymmetric QA / Search & Clustering.
33
- - 8 Datasets from Stackexchange and StackOverflow, PAWS, Gender Evaluation uploaded to HuggingFace Hub.
34
- - Achieve SOTA on multiple general purpose Sentence Similarity evaluation tasks by utilizing large TPU memory to maximize
35
  customized Contrastive Loss. [Full Evaluation here](https://docs.google.com/spreadsheets/d/1vXJrIg38cEaKjOG5y4I4PQwAQFUmCkohbViJ9zj_Emg/edit#gid=1809754143).
36
- - Gender Bias Demonstration that explores inherent bias in general purpose datasets.
37
- - Search / Clustering Demonstration that showcases real-world use-cases for Sentence Embeddings.
38
 
39
  ''')
40
 
 
18
  We trained three general-purpose flax-sentence-embeddings models: a **distilroberta base**, a **mpnet base** and a **minilm-l6**.
19
  The models were trained on a dataset comprising of [1 Billion+ training corpus](https://huggingface.co/flax-sentence-embeddings/all_datasets_v4_MiniLM-L6#training-data) with the v3 setup.
20
 
21
+ In addition, we trained [20 models](https://huggingface.co/flax-sentence-embeddings) focused on general-purpose, QuestionAnswering and Code search and **achieved SOTA on multiple benchmarks.**
22
  We also uploaded [8 datasets](https://huggingface.co/flax-sentence-embeddings) specialized for Question Answering, Sentence-Similiarity and Gender Evaluation.
23
  You can view our models and datasets [here](https://huggingface.co/flax-sentence-embeddings).
24
 
 
29
 
30
  ## Contributions
31
 
32
+ - **20 performant Sentence Embedding models** that can be utilized for Sentence Simliarity / Asymmetric QA / Search & Clustering.
33
+ - **8 Datasets** from Stackexchange and StackOverflow, PAWS, Gender Evaluation uploaded to HuggingFace Hub.
34
+ - **Achieve SOTA** on multiple general purpose Sentence Similarity evaluation tasks by utilizing large TPU memory to maximize
35
  customized Contrastive Loss. [Full Evaluation here](https://docs.google.com/spreadsheets/d/1vXJrIg38cEaKjOG5y4I4PQwAQFUmCkohbViJ9zj_Emg/edit#gid=1809754143).
36
+ - **Gender Bias demonstration** that explores inherent bias in general purpose datasets.
37
+ - **Search / Clustering demonstration** that showcases real-world use-cases for Sentence Embeddings.
38
 
39
  ''')
40