RichardErkhov/Crataco_-_Pythia-160M-Deduped-Adventure-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Pythia-160M-Deduped-Adventure - GGUF

• —Model creator: https://huggingface.co/Crataco/
• —Original model: https://huggingface.co/Crataco/Pythia-160M-Deduped-Adventure/

Original model description: --- tags:

• —generatedfromtrainer model-index:
• —name: pythia-160m-deduped-aid results: [] ---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

pythia-160m-deduped-aid

Model description

This model is a finetune of EleutherAI/pythia-160m-deduped (from when it was instead pythia-125m-deduped), on the `text_adventures.txt` dataset originally intended for AI Dungeon 2. Performance will be very poor, as expected by the small model, and generations may be offensive thanks to its training data.

This model was trained for testing purposes as the successor to Merry/AID-Neo-125M and was intended for use with KoboldAI. A temperature of 0.5 and a repetition penalty of 1.05 were tested.

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 5e-05
• —trainbatchsize: 2
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 3.0

Training results

Framework versions

• —Transformers 4.26.0.dev0
• —Pytorch 1.13.1+cu116
• —Datasets 2.8.0
• —Tokenizers 0.13.2