thesa / README.md
johnhandleyd's picture
Update README.md
4a1cf8c verified
|
raw
history blame
1.68 kB
metadata
license: mit
base_model: TheBloke/zephyr-7B-alpha-GPTQ
tags:
  - generated_from_trainer
  - gptq
  - peft
model-index:
  - name: thesa
    results: []
datasets:
  - loaiabdalslam/counselchat
language:
  - en
pipeline_tag: text-generation

Thesa: A Therapy Chatbot πŸ‘©πŸ»β€βš•οΈ

Thesa is an experimental project of a therapy chatbot trained on mental health data and fine-tuned with the Zephyr GPTQ model that uses quantization to decrease high computatinal and storage costs.

Model description

Intended uses & limitations

This model is purely experimental and should not be used as substitute for a mental health professional.

Training evaluation

Training loss: loss

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • warmup_ratio: 0.1
  • train_batch_size: 8
  • eval_batch_size: 8
  • gradient_accumulation_steps: 1
  • seed: 35
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP
  • fp16: True

Learning rate overtime (warm up ratio was used during training): lr

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
  • Accelerate 0.27.2
  • PEFT 0.8.2
  • Auto-GPTQ 0.6.0
  • TRL 0.7.11
  • Optimum 1.17.1
  • Bitsandbytes 0.42.0