Quantization made by Richard Erkhov.

Github

Discord

Request more models

TinyLlama-1.1B-Chat-v0.1fictionalarcchallengeKorean_v1 - GGUF

• Model creator: https://huggingface.co/yzhuang/
• Original model: https://huggingface.co/yzhuang/TinyLlama-1.1B-Chat-v0.1fictionalarcchallengeKorean_v1/

Original model description:

• trl
• sft
• generatedfromtrainer

• generator

• name: TinyLlama-1.1B-Chat-v0.1fictionalarcchallengeKorean_v1

TinyLlama-1.1B-Chat-v0.1fictionalarcchallengeKorean_v1

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v0.1 on the generator dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learningrate: 5e-05
• trainbatchsize: 1
• evalbatchsize: 2
• seed: 42
• gradientaccumulationsteps: 16
• totaltrainbatchsize: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lrschedulertype: linear
• num_epochs: 36

Training results

Framework versions

• Transformers 4.40.2
• Pytorch 2.1.0a0+32f93b1
• Datasets 2.19.1
• Tokenizers 0.19.1