README.md

metadata

language:
  - pt
license: apache-2.0
library_name: transformers
tags:
  - text-generation-inference
  - TensorBlock
  - GGUF
datasets:
  - nicholasKluge/instruct-aira-dataset-v3
  - cnmoro/GPT4-500k-Augmented-PTBR-Clean
  - rhaymison/orca-math-portuguese-64k
  - nicholasKluge/reward-aira-dataset
metrics:
  - perplexity
pipeline_tag: text-generation
widget:
  - text: >-
      <instruction>Cite algumas bandas de rock brasileiras
      famosas.</instruction>
    example_title: Exemplo
  - text: >-
      <instruction>Invente uma história sobre um encanador com poderes
      mágicos.</instruction>
    example_title: Exemplo
  - text: >-
      <instruction>Qual cidade é a capital do estado do Rio Grande do
      Sul?</instruction>
    example_title: Exemplo
  - text: >-
      <instruction>Diga o nome de uma maravilha culinária característica da
      cosinha Portuguesa?</instruction>
    example_title: Exemplo
inference:
  parameters:
    repetition_penalty: 1.2
    temperature: 0.2
    top_k: 20
    top_p: 0.2
    max_new_tokens: 150
co2_eq_emissions:
  emissions: 21890
  source: CodeCarbon
  training_type: pre-training
  geographical_location: Germany
  hardware_used: NVIDIA A100-SXM4-80GB
base_model: TucanoBR/Tucano-1b1-Instruct
model-index:
  - name: Tucano-1b1-Instruct
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: CALAME-PT
          type: NOVA-vision-language/calame-pt
          split: all
          args:
            num_few_shot: 0
        metrics:
          - type: acc
            value: 56.55
            name: accuracy
        source:
          url: https://huggingface.co/datasets/NOVA-vision-language/calame-pt
          name: Context-Aware LAnguage Modeling Evaluation for Portuguese
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: LAMBADA-PT
          type: TucanoBR/lambada-pt
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: acc
            value: 35.53
            name: accuracy
        source:
          url: https://huggingface.co/datasets/TucanoBR/lambada-pt
          name: LAMBADA-PT
      - 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: 21.06
            name: accuracy
        source:
          url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
          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: 26.01
            name: accuracy
        source:
          url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
          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: 26.47
            name: accuracy
        source:
          url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
          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: 67.78
            name: f1-macro
        source:
          url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
          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: 10
        metrics:
          - type: pearson
            value: 8.88
            name: pearson
        source:
          url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
          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
          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: 31.28
            name: f1-macro
        source:
          url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
          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
          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: 22.03
            name: f1-macro
        source:
          url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: ARC-Challenge (PT)
          type: arc_pt
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 30.77
            name: normalized accuracy
        source:
          url: https://github.com/nlp-uoregon/mlmm-evaluation
          name: Evaluation Framework for Multilingual Large Language Models
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (PT)
          type: hellaswag_pt
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 43.5
            name: normalized accuracy
        source:
          url: https://github.com/nlp-uoregon/mlmm-evaluation
          name: Evaluation Framework for Multilingual Large Language Models
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (PT)
          type: truthfulqa_pt
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 41.14
            name: bleurt
        source:
          url: https://github.com/nlp-uoregon/mlmm-evaluation
          name: Evaluation Framework for Multilingual Large Language Models
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Alpaca-Eval (PT)
          type: alpaca_eval_pt
          args:
            num_few_shot: 0
        metrics:
          - type: lc_winrate
            value: 8.8
            name: length controlled winrate
        source:
          url: https://github.com/tatsu-lab/alpaca_eval
          name: AlpacaEval

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

TucanoBR/Tucano-1b1-Instruct - GGUF

This repo contains GGUF format model files for TucanoBR/Tucano-1b1-Instruct.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Run them on the TensorBlock client using your local machine ↗

Prompt template

<instruction>{prompt}</instruction>

Model file specification

Filename	Quant type	File Size	Description
Tucano-1b1-Instruct-Q2_K.gguf	Q2_K	0.432 GB	smallest, significant quality loss - not recommended for most purposes
Tucano-1b1-Instruct-Q3_K_S.gguf	Q3_K_S	0.499 GB	very small, high quality loss
Tucano-1b1-Instruct-Q3_K_M.gguf	Q3_K_M	0.548 GB	very small, high quality loss
Tucano-1b1-Instruct-Q3_K_L.gguf	Q3_K_L	0.592 GB	small, substantial quality loss
Tucano-1b1-Instruct-Q4_0.gguf	Q4_0	0.637 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Tucano-1b1-Instruct-Q4_K_S.gguf	Q4_K_S	0.640 GB	small, greater quality loss
Tucano-1b1-Instruct-Q4_K_M.gguf	Q4_K_M	0.668 GB	medium, balanced quality - recommended
Tucano-1b1-Instruct-Q5_0.gguf	Q5_0	0.766 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Tucano-1b1-Instruct-Q5_K_S.gguf	Q5_K_S	0.766 GB	large, low quality loss - recommended
Tucano-1b1-Instruct-Q5_K_M.gguf	Q5_K_M	0.782 GB	large, very low quality loss - recommended
Tucano-1b1-Instruct-Q6_K.gguf	Q6_K	0.903 GB	very large, extremely low quality loss
Tucano-1b1-Instruct-Q8_0.gguf	Q8_0	1.170 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Tucano-1b1-Instruct-GGUF --include "Tucano-1b1-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Tucano-1b1-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'