README.md

---
language:
- pt
- en
license: other
model-index:
- name: cabra13b
  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: 48.85
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      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: 40.89
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      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: 35.31
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      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: 85.55
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      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: 57.19
      name: pearson
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      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: 45.45
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      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: 77.78
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      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: 64.13
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      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: 53.37
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/cabra13b
      name: Open Portuguese LLM Leaderboard
---

**Conheça os nossos outros modelos (bem melhores): [Cabra](https://huggingface.co/collections/botbot-ai/models-6604c2069ceef04f834ba99b)**

O Cabra 13b é um qlora finetune do [LLaMA 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) usando o dataset [PortugueseDolly]( https://huggingface.co/datasets/nicolasdec/PortugueseDolly), tradução do [Databricks Dolly 15k]( https://huggingface.co/datasets/databricks/databricks-dolly-15k).

*Somente para demonstração e pesquisa. Proibido para uso comercial. 

O modelo precisa de mais treinamento, e pode gerar mentira ou inverdades. 


# [Open Portuguese LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/nicolasdec/cabra13b)

|          Metric          | Value  |
|--------------------------|--------|
|Average                   |**56.5**|
|ENEM Challenge (No Images)|   48.85|
|BLUEX (No Images)         |   40.89|
|OAB Exams                 |   35.31|
|Assin2 RTE                |   85.55|
|Assin2 STS                |   57.19|
|FaQuAD NLI                |   45.45|
|HateBR Binary             |   77.78|
|PT Hate Speech Binary     |   64.13|
|tweetSentBR               |   53.37|