Hugging Face's logo

DILAB-HYU
/
koquality-ko-ref-llama2-7b

Text Generation
Transformers
PyTorch
Korean
llama
KoQuality
text-generation-inference
Inference Endpoints
Model card Files Community

This model is a instruct-tuned hyunseoki/ko-ref-llama2-7b model using koquality.

Training hyperparameters

  • learning_rate: 5e-5
  • train_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU (A30 24G) + CPU Offloading (384GB)
  • num_devices: 2
  • gradient_accumulation_steps: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2.0

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.11.0
  • deepspeed 0.9.5
Downloads last month
4,834
Inference Examples
Text Generation
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for DILAB-HYU/koquality-ko-ref-llama2-7b

Base model

hyunseoki/ko-ref-llama2-7b
Finetuned
(2)
this model

Dataset used to train DILAB-HYU/koquality-ko-ref-llama2-7b