Model Card for Model ID

Instruct Fine-tuning Gemma using qLora and Supervise Finetuning

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by:
  • Funded by [optional]: azurehorizon
  • Model type: gemma-2b-it
  • Language(s) (NLP): English,
  • License: gemma
  • Finetuned from model [optional]: gemma-2b-it

Training Data

TokenBender/code_instructions_122k_alpaca_style

Summary

'global_step'=100, 'train_samples_per_second': 0.501, 'train_steps_per_second': 0.125, 'total_flos': 907555205713920.0, 'train_loss': 0.99025949716568,

  • Hardware Type: T4 GPU
  • Hours used: 0:13 H
  • Cloud Provider: Google Colab
Downloads last month
-
Safetensors
Model size
3B params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support