Downloads · 30 days
20
0% of all-time downloads
polyglot-ko-12.8b-Inst-All
nayohan/polyglot-ko-12.8b-Inst-All
polyglot-ko-12.8b-Inst-All is a text generation model from nayohan. 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 instruct-tuned poylglot-ko-5.8b model, using full [Kullm, OIG, KoAlpaca] Instruction dataset. koqualityraw.json - 96step
All-time downloads
25K
Public
Parameters
12.9B
51.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors51.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- gpt_neox
- Access
- Public
- Created
- Nov 16, 2023
- Updated
- Nov 17, 2023
- SHA
- 288ddc14
Base models
Datasets
Model card
From the Hugging Face model README
This model is a instruct-tuned poylglot-ko-5.8b model, using full [Kullm, OIG, KoAlpaca] Instruction dataset. koquality_raw.json -> 96step
Training hyperparameters
- learning_rate: 5e-5
- seed: 42
- distributed_type: multi-GPU (A100 80G)
- num_devices: 6
- train_batch_size: 4
- gradient_accumulation_steps: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6
- deepspeed 0.11.1
- accelerate 0.24.1
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_neox
- License
- apache-2.0
- Languages
- ko
- Created
- Nov 16, 2023
- Updated
- Nov 17, 2023