RichardErkhov/DooDooHyun_-_AIFT-Yi-Ko-6B-ao-instruct-all-v0.54-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

AIFT-Yi-Ko-6B-ao-instruct-all-v0.54 - GGUF

• —Model creator: https://huggingface.co/DooDooHyun/
• —Original model: https://huggingface.co/DooDooHyun/AIFT-Yi-Ko-6B-ao-instruct-all-v0.54/

Original model description: --- license: other base_model: beomi/Yi-Ko-6B tags:

• —generatedfromtrainer model-index:
• —name: AIFT-Yi-Ko-6B-ao-instruct-all-v0.54 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. -->

AIFT-Yi-Ko-6B-ao-instruct-all-v0.54

This model is a fine-tuned version of beomi/Yi-Ko-6B on an unknown 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:

• —learning_rate: 2e-05
• —trainbatchsize: 4
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 1.0
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.36.2
• —Pytorch 2.1.2+cu121
• —Datasets 2.0.0
• —Tokenizers 0.15.0