mistral-pdf-to-quizz-7b

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.1-GPTQ.

Model description

• Trained on 168 prompts that generate in order to generate a multiple question choices responses (https://huggingface.co/datasets/fbellame/pdf_to_quizz_mistral)

  <s>[INST] You are a teacher preparing questions for a quiz. Given the following document, please generate 1 multiple-choice questions (MCQs) with 4 options and a corresponding answer letter based on the document.\\n\\nExample question:\\n\\nQuestion: question here\\nCHOICE_A: choice here\\nCHOICE_B: choice here\\nCHOICE_C: choice here\\nCHOICE_D: choice here\\nAnswer: A or B or C or D\\n\\nThese questions should be detailed and solely based on the information provided in the document.\\n here are the inputs \\n{doc}\\n[/INST]
  
  doc=In 1229, the King had to struggle with a long lasting strike at the University of Paris. The Quartier Latin was strongly hit by these strikes.
  
  question: What was the cause of the strike at the University of Paris in 1229?
  choice_A: The King's interference in university affairs
  choice_B: A shortage of resources for the university
  choice_C: A disagreement between faculty members
  choice_D: The Quartier Latin being strongly hit by a natural disaster
  reponse: choice_B
  

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• training_steps: 600
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1