Downloads · 30 days
108
0% of all-time downloads
kullm-polyglot-12.8b-v2
nlpai-lab/kullm-polyglot-12.8b-v2
kullm-polyglot-12.8b-v2 is a text generation model from nlpai-lab. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of EleutherAI/polyglot-ko-12.8b on a KULLM v2
All-time downloads
116K
Public
Repo size
51.9 GB
Likes
53
Public
Repo makeup
Click a slice to open those files.
.bin26 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- gpt_neox
- Access
- Public
- Created
- May 31, 2023
- Updated
- May 31, 2023
- SHA
- 9e0c9be8
Model card
From the Hugging Face model README
KULLM-Polyglot-12.8B-v2
This model is a fine-tuned version of EleutherAI/polyglot-ko-12.8b on a KULLM v2
Detail Codes are available at KULLM Github Repository
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-4
- train_batch_size: 6
- seed: 42
- distributed_type: multi-GPU (A100 80G)
- num_devices: 4
- gradient_accumulation_steps: 21.3
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8.0
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_neox
- License
- apache-2.0
- Languages
- ko
- Created
- May 31, 2023
- Updated
- May 31, 2023