Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
gollm-12.8b-instruct-v1.1d – AI Model by tlphams | AlphaNeural AI
You can deploy this model and start earning money today!
tlphams
/
gollm-12.8b-instruct-v1.1d
like
0
transformers
pytorch
gpt_neox
text-generation
generated_from_trainer
EleutherAI/polyglot-ko-12.8b
finetune
cc-by-nc-sa-4.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
gridone-ko-llm-12.8b-v1.1d-supervised
This model is a fine-tuned version of
EleutherAI/polyglot-ko-12.8b
on modified KoAlpaca v1.1 dataset (1.1d), using supervised-style finetuning.
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
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 8
early_stop_epoch: 4
Framework versions
Transformers 4.32.0.dev0
Pytorch 2.0.0+cu117
Datasets 2.11.0
Tokenizers 0.13.3
