Hugging Face's logo

ToastyPigeon
/
Mistral-Nemo-12B-Adventure-QLoRA

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
Mistral-Nemo-12B-Adventure-QLoRA / README.md
ToastyPigeon's picture
ToastyPigeon
Update README.md
5861f53 verified
preview code
|
raw
history blame contribute delete
1.66 kB
metadata
base_model: unsloth/Mistral-Nemo-Base-2407
library_name: peft
license: apache-2.0
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: adventure-nemo-ws
    results: []

Built with Axolotl

Mistral-Nemo-12B-Adventure-QLoRA

Another QLoRA on Mistral Nemo Base, this time with Spring Dragon and Skein data included. ~29M tokens total of text adventure data.

This was trained in completion format where user input is given as > User input. Set > as a stopping string and preface your input with > to use with classic text completion mode.

This method of use is set up as default in Kobold Lite's Adventure mode.

Again, no instruct format was trained into this.

Apply to a Nemo model and use whatever instruct format that model uses - the style (and deadliness) of the LoRA carries over to instruct usage as well.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.00025
  • train_batch_size: 4
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine_with_min_lr
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1

Framework versions

  • PEFT 0.12.0
  • Transformers 4.45.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1