metadata

license: mit
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: TheBloke/zephyr-7B-alpha-GPTQ
model-index:
  - name: zephyr-support-chatbot
    results: []
datasets:
  - bitext/Bitext-customer-support-llm-chatbot-training-dataset
pipeline_tag: text-generation

zephyr-7B-alpha-GPTQ

Model description

Large language models have achieved groundbreaking success in the field of natural language processing (NLP). However, since these models are generally trained for general-purpose tasks, they may not perform optimally for specific tasks. Therefore, fine-tuning these large models for specific tasks is a common practice. In this article, we will delve into the process of fine-tuning and adapting the Zephyr-7B-alpha-GPTQ, a large language model, for a particular task.

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: 250
mixed_precision_training: Native AMP

Framework versions

PEFT 0.10.0
Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Author

Anezatra Katedram