TODO

• run evaluations of all datasets on

  • gpt4, gpt3.5
  • Gemini
  • HF
    • Mistral
      • mistralai/Mixtral-8x7B-Instruct-v0.1 · Hugging Face

        • This format must be strictly respected, otherwise the model will generate sub-optimal outputs.

      • mistralai/Mixtral-8x7B-v0.1 · Hugging Face
    • Ukrainian Instruct models
      • Radu1999/Mistral-Instruct-Ukrainian-SFT · Hugging Face
      • robinhad/ualpaca-7b-llama · Hugging Face
        • robinhad/kruk: Ukrainian instruction-tuned language models and datasets
    • Random
      • Tereveni-AI/gpt2-124M-uk-fiction · Hugging Face for ua-CBT
  • other
    • Look for more:
      • Models - Hugging Face

• calculate and graph human baselines