README.md

metadata

license: llama2
model-index:
  - name: cabrita_7b_pt_850000
    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: 22.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=22h/cabrita_7b_pt_850000
          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: 23.09
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=22h/cabrita_7b_pt_850000
          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: 29.2
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=22h/cabrita_7b_pt_850000
          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: 33.33
            name: f1-macro
          - type: pearson
            value: 12.65
            name: pearson
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=22h/cabrita_7b_pt_850000
          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: 17.72
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=22h/cabrita_7b_pt_850000
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HateBR Binary
          type: eduagarcia/portuguese_benchmark
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: f1_macro
            value: 55.98
            name: f1-macro
          - type: f1_macro
            value: 49.02
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=22h/cabrita_7b_pt_850000
          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: 45.75
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=22h/cabrita_7b_pt_850000
          name: Open Portuguese LLM Leaderboard

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Average	32.14
ENEM Challenge (No Images)	22.53
BLUEX (No Images)	23.09
OAB Exams	29.20
Assin2 RTE	33.33
Assin2 STS	12.65
FaQuAD NLI	17.72
HateBR Binary	55.98
PT Hate Speech Binary	49.02
tweetSentBR	45.75