README.md

metadata

license: other
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
datasets:
  - generator
base_model: google/gemma-7b
model-index:
  - name: gemma-7b-dolly-chatml
    results: []

gemma-7b-dolly-chatml

This model is a fine-tuned version of google/gemma-7b with philschmid/gemma-tokenizer-chatml tokenizer on the philschmid/dolly-15k-oai-style using the chatML format.

The model was fine-tuned with the following script using Lora (no, qlora). I also included a inference script to make sure it works since there were some issues with Gemma. Results of the inference test are

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: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Framework versions

• PEFT 0.8.2
• Transformers 4.38.1
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0