RichardErkhov/GOODYEONSU_-_Qwen2.5-0.5B-Instruct-ymg-finetuned-0925-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2.5-0.5B-Instruct-ymg-finetuned-0925 - GGUF

• —Model creator: https://huggingface.co/GOODYEONSU/
• —Original model: https://huggingface.co/GOODYEONSU/Qwen2.5-0.5B-Instruct-ymg-finetuned-0925/

Original model description: --- libraryname: transformers license: apache-2.0 basemodel: Qwen/Qwen2.5-0.5B-Instruct tags:

• —trl
• —sft
• —generatedfromtrainer model-index:
• —name: Qwen2.5-0.5B-Instruct-ymg-finetuned-0925 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. -->

Qwen2.5-0.5B-Instruct-ymg-finetuned-0925

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct 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: 5e-05
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 3
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 384
• —totalevalbatch_size: 24
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: constant
• —lrschedulerwarmup_ratio: 0.03
• —num_epochs: 3

Training results

Framework versions

• —Transformers 4.44.2
• —Pytorch 2.4.0+cu121
• —Datasets 2.20.0
• —Tokenizers 0.19.1