recogna's picture
Update README.md
5222387 verified
metadata
license: mit
model-index:
  - name: phibode_1_5_ultraalpaca
    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: 23.58
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          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: 20.72
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          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: 24.87
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          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: 69.07
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          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: 4.94
            name: pearson
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          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: 43.97
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          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: 34.94
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          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: 41.23
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: tweetSentBR
          type: eduagarcia/tweetsentbr_fewshot
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: f1_macro
            value: 24.19
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/phibode_1_5_ultraalpaca
          name: Open Portuguese LLM Leaderboard

Phi-Bode

Phi-Bode Logo

Phi-Bode é um modelo de linguagem ajustado para o idioma português, desenvolvido a partir do modelo base Phi-1.5B fornecido pela Microsoft. Este modelo foi refinado através do processo de fine-tuning utilizando o dataset UltraAlpaca. O principal objetivo deste modelo é ser viável para pessoas que não possuem recursos computacionais disponíveis para o uso de LLMs (Large Language Models). Ressalta-se que este é um trabalho em andamento e o modelo ainda apresenta problemas na geração de texto em português.

Características Principais

  • Modelo Base: Phi-1.5B, criado pela Microsoft, com 1.3 bilhões de parâmetros.
  • Dataset para Fine-tuning: UltraAlpaca
  • Treinamento: O treinamento foi realizado a partir do fine-tuning completo do phi-1.5.

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard

Metric Value
Average 31.95
ENEM Challenge (No Images) 23.58
BLUEX (No Images) 20.72
OAB Exams 24.87
Assin2 RTE 69.07
Assin2 STS 4.94
FaQuAD NLI 43.97
HateBR Binary 34.94
PT Hate Speech Binary 41.23
tweetSentBR 24.19