van-ng's picture
Update README.md
c12666f verified
metadata
license: mit
base_model: EleutherAI/pythia-160m
tags:
  - generated_from_trainer
model-index:
  - name: pythia-XYZCompany-1000-steps
    results: []

This model is a question-answer chatbot for XYZCompany. It can answer questions related to the company. It is a fine-tuned version of pythia-160m on XYZCompany's dataset containing question-answer pairs.

Model description

More information needed

Intended uses & limitations

You can ask questions about XYZCompany, an AI company specialized in LLMs and other AI code.

Example questions:

  1. What can XYZCompany do?
  2. Does XYZCompany have the ability to understand and generate code for audio generative tasks?
  3. How to access XYZCompany's LLM tools?

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1
  • training_steps: 1000

Training results

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.1.2
  • Datasets 2.17.1
  • Tokenizers 0.13.2