cnmoro's picture
Fixing some errors of the leaderboard evaluation results in the ModelCard yaml (#5)
3b26b76 verified
metadata
language:
  - en
  - pt
datasets:
  - cnmoro/WizardVicuna-PTBR-Instruct-Clean
model-index:
  - name: Mistral-7B-Portuguese
    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: 58.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          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: 48.68
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          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: 37.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          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: 90.31
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          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: 76.55
            name: pearson
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          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: 58.84
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          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: 79.21
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          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: 68.87
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          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: 64.71
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
          name: Open Portuguese LLM Leaderboard

This is a finetuned version of mistralai/Mistral-7B-Instruct-v0.2 using unsloth on a instruct portuguese dataset, as an attempt to improve the performance of the model on the language.

No benchmarks have been executed yet.

The original prompt format was used:

<s>[INST] {Prompt goes here} [/INST]

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Average 64.7
ENEM Challenge (No Images) 58.08
BLUEX (No Images) 48.68
OAB Exams 37.08
Assin2 RTE 90.31
Assin2 STS 76.55
FaQuAD NLI 58.84
HateBR Binary 79.21
PT Hate Speech Binary 68.87
tweetSentBR 64.71