readme

README.md

@@ -3,12 +3,11 @@ language:
 - en
 - pt
 tags:
-- bart
-- seq2seq
 - summarization
 license: apache-2.0
 datasets:
 - samsum
+- csebuetnlp/xlsum
 widget:
 - text: |
     Bruno: Ei, você tem o número da Betty?
@@ -17,17 +16,29 @@ widget:
     Kleber: De acordo com minha pesquisa o número é 35 9 9898-6142
     Bruno: Obrigado.
 model-index:
-- name: bart-large-xsum-samsum
+- name: cqi_brain_memory_summarizer_large_pt_v0 
   results:
   - task:
-      name: Abstractive Text Summarization
-      type: abstractive-text-summarization
+      name: summarization
+      type: Summarization
     dataset:
       name: >-
         SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive
         Summarization
       type: samsum
+      name: xsum
+      type: xsum
+      config: default
+      split: test
     metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 36.5002
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 13.934
+      verified: true
     - name: Validation ROUGE-1
       type: rouge-1
       value: 54.3921
@@ -49,39 +60,7 @@ model-index:
 metrics:
 - accuracy
 ---
-## `bart-large-xsum-samsum`
-This model was obtained by fine-tuning `facebook/bart-large-xsum` on [Samsum](https://huggingface.co/datasets/samsum) dataset.
-## Usage
-```python
-from transformers import pipeline
+### `CQI Brain - Sumarização de Textos Longos PT V0`
+## `Aplicação de Pré tratamento para armazenamento de memórias`
 
-summarizer = pipeline("summarization", model="lidiya/bart-large-xsum-samsum")
-conversation = '''Hannah: Hey, do you have Betty's number?
-Amanda: Lemme check
-Amanda: Sorry, can't find it.
-Amanda: Ask Larry
-Amanda: He called her last time we were at the park together
-Hannah: I don't know him well
-Amanda: Don't be shy, he's very nice
-Hannah: If you say so..
-Hannah: I'd rather you texted him
-Amanda: Just text him 🙂
-Hannah: Urgh.. Alright
-Hannah: Bye
-Amanda: Bye bye                                       
-'''
-summarizer(conversation)
-```
-## Training procedure
-- Colab notebook: https://colab.research.google.com/drive/1dul0Sg-TTMy9xZCJzmDRajXbyzDwtYx6?usp=sharing
-## Results
-| key | value |
-| --- | ----- |
-| eval_rouge1 | 54.3921 |
-| eval_rouge2 | 29.8078 |
-| eval_rougeL | 45.1543 |
-| eval_rougeLsum | 49.942 |
-| test_rouge1 | 53.3059 |
-| test_rouge2 | 28.355 |
-| test_rougeL | 44.0953 |
-| test_rougeLsum | 48.9246 |
+# `Work in progress`