Polyglot-Ko 1.3B
A Korean autoregressive language model developed by the EleutherAI Polyglot team. The released weights support text completion and further adaptation.
Research release
Korean modeling at this scale
This is the smallest of the four documented Polyglot-Ko sizes. Its 24-layer network provides a Korean-specific starting point for fine-tuning without requiring the larger family checkpoints.polyglot-ko-1.3b model cardpolyglot-ko-1.3b model configuration
Training data and use
The training corpus was curated by TUNiB. It includes Korean blogs, news, patents and other text. The card says the underlying corpus will not be released for public use, although the model weights use Apache 2.0.polyglot-ko-1.3b model card
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | EleutherAI/polyglot-ko-1.3b |
| Context window | 2,048 tokens Maximum position count in the released model configuration. polyglot-ko-1.3b model configuration |
| Parameters | 1,331,810,304polyglot-ko-1.3b model card |
| Language | Koreanpolyglot-ko-1.3b model card |
| License | Apache 2.0polyglot-ko-1.3b model card |
Related models
- Polyglot-Ko 12.8B
EleutherAI · Polyglot-Ko
The largest documented Polyglot-Ko base model, trained on Korean text.
Launch date not confirmedResearch releaseDownloadable - Polyglot-Ko 3.8B
EleutherAI · Polyglot-Ko
A Korean text-completion model with 32 Transformer layers.
Launch date not confirmedResearch releaseDownloadable - Polyglot-Ko 5.8B
EleutherAI · Polyglot-Ko
A wider Korean base model with 28 layers and downloadable weights.
Launch date not confirmedResearch releaseDownloadable