Update README.md

README.md

@@ -1,31 +1,31 @@
 ---
+license: apache-2.0
+datasets:
+- nicholasKluge/instruct-aira-dataset-v2
 language:
 - pt
-license: apache-2.0
+metrics:
+- accuracy
 library_name: transformers
+pipeline_tag: text-generation
 tags:
 - alignment
 - instruction tuned
 - text generation
 - conversation
 - assistant
-datasets:
-- nicholasKluge/instruct-aira-dataset-v2
-metrics:
-- accuracy
-pipeline_tag: text-generation
 widget:
-- text: <s><instruction>Cite algumas bandas de rock famosas da década de 1960.</instruction>
+- text: "<s><instruction>Cite algumas bandas de rock famosas da década de 1960.</instruction>"
   example_title: Exemplo
-- text: <s><instruction>Quantos planetas existem no sistema solar?</instruction>
+- text: "<s><instruction>Quantos planetas existem no sistema solar?</instruction>"
   example_title: Exemplo
-- text: <s><instruction>Qual é o futuro do ser humano?</instruction>
+- text: "<s><instruction>Qual é o futuro do ser humano?</instruction>"
   example_title: Exemplo
-- text: <s><instruction>Qual o sentido da vida?</instruction>
+- text: "<s><instruction>Qual o sentido da vida?</instruction>"
   example_title: Exemplo
-- text: <s><instruction>Como imprimir hello world em python?</instruction>
+- text: "<s><instruction>Como imprimir hello world em python?</instruction>"
   example_title: Exemplo
-- text: <s><instruction>Invente uma história sobre um encanador com poderes mágicos.</instruction>
+- text: "<s><instruction>Invente uma história sobre um encanador com poderes mágicos.</instruction>"
   example_title: Exemplo
 inference:
   parameters:
@@ -42,153 +42,6 @@ co2_eq_emissions:
   training_type: fine-tuning
   geographical_location: United States of America
   hardware_used: NVIDIA A100-SXM4-40GB
-model-index:
-- name: TeenyTinyLlama-460m-Chat
-  results:
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: ENEM Challenge (No Images)
-      type: eduagarcia/enem_challenge
-      split: train
-      args:
-        num_few_shot: 3
-    metrics:
-    - type: acc
-      value: 20.29
-      name: accuracy
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: BLUEX (No Images)
-      type: eduagarcia-temp/BLUEX_without_images
-      split: train
-      args:
-        num_few_shot: 3
-    metrics:
-    - type: acc
-      value: 25.45
-      name: accuracy
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: OAB Exams
-      type: eduagarcia/oab_exams
-      split: train
-      args:
-        num_few_shot: 3
-    metrics:
-    - type: acc
-      value: 26.74
-      name: accuracy
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: Assin2 RTE
-      type: assin2
-      split: test
-      args:
-        num_few_shot: 15
-    metrics:
-    - type: f1_macro
-      value: 43.77
-      name: f1-macro
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: Assin2 STS
-      type: eduagarcia/portuguese_benchmark
-      split: test
-      args:
-        num_few_shot: 15
-    metrics:
-    - type: pearson
-      value: 4.52
-      name: pearson
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: FaQuAD NLI
-      type: ruanchaves/faquad-nli
-      split: test
-      args:
-        num_few_shot: 15
-    metrics:
-    - type: f1_macro
-      value: 34.0
-      name: f1-macro
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: HateBR Binary
-      type: ruanchaves/hatebr
-      split: test
-      args:
-        num_few_shot: 25
-    metrics:
-    - type: f1_macro
-      value: 33.49
-      name: f1-macro
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: PT Hate Speech Binary
-      type: hate_speech_portuguese
-      split: test
-      args:
-        num_few_shot: 25
-    metrics:
-    - type: f1_macro
-      value: 22.99
-      name: f1-macro
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: tweetSentBR
-      type: eduagarcia-temp/tweetsentbr
-      split: test
-      args:
-        num_few_shot: 25
-    metrics:
-    - type: f1_macro
-      value: 18.13
-      name: f1-macro
-    source:
-      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
-      name: Open Portuguese LLM Leaderboard
 ---
 # TeenyTinyLlama-460m-Chat
 
@@ -245,7 +98,7 @@ responses = model.generate(**inputs, num_return_sequences=2)
 print(f"Pergunta: 👤 {question}\n")
 
 for i, response in  enumerate(responses):
-	print(f'Resposta {i+1}: 🤖 {tokenizer.decode(response, skip_special_tokens=True).replace(question, "")}')
+  print(f'Resposta {i+1}: 🤖 {tokenizer.decode(response, skip_special_tokens=True).replace(question, "")}')
 ```
 
 The model will output something like:
@@ -364,7 +217,6 @@ All the shown results are the higher accuracy scores achieved on the respective
 ## Cite as 🤗
 
 ```latex
-
 @misc{correa24ttllama,
   title = {TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese},
   author = {Corr{\^e}a, Nicholas Kluge and Falk, Sophia and Fatimah, Shiza and Sen, Aniket and De Oliveira, Nythamar},
@@ -372,6 +224,15 @@ All the shown results are the higher accuracy scores achieved on the respective
   year={2024}
 }
 
+@misc{correa24ttllama,
+  doi = {10.1016/j.mlwa.2024.100558},
+  url = {https://www.sciencedirect.com/science/article/pii/S2666827024000343},
+  title = {TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese},
+  author = {Corr{\^e}a, Nicholas Kluge and Falk, Sophia and Fatimah, Shiza and Sen, Aniket and De Oliveira, Nythamar},
+  journal={Machine Learning With Applications},
+  publisher = {Springer},
+  year={2024}
+}
 ```
 
 ## Funding
@@ -381,4 +242,3 @@ This repository was built as part of the RAIES ([Rede de Inteligência Artificia
 ## License
 
 TeenyTinyLlama-460m-Chat is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
-