FinGPT 8B
FinGPT 8B is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series. It uses the BLOOM architecture and is not an OpenAI GPT-3 checkpoint.
Model design and training
32 layers, width 4,096 and 32 attention heads. The card reports 300 billion training tokens. The Finnish corpus combines web text, news, books, Wikipedia and discussion data. This is a pure language model, without dialogue or question-answering instruction tuning.gpt3-finnish-8B: official model card
Practical assessment
Practical guidance. The 8B name refers to a 7.5-billion-parameter release. Compare it with the 3B model using the same prompts and output controls to make scale differences interpretable. Add a separate task-training stage if answers must follow structured instructions.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | gpt3-finnish-8BFinnish GPT-3 8B |
| Model size | 7.5 billion parameters in the architecture table.gpt3-finnish-8B: official model card |
| License | Apache 2.0.gpt3-finnish-8B: official model card |
| Training state | Pretrained base; not instruction-tuned.gpt3-finnish-8B: official model card |
Related models
- FinGPT 13B
TurkuNLP · FinGPT
FinGPT 13B is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.
Launch date not confirmedDownloadable - FinGPT Small
TurkuNLP · FinGPT
FinGPT Small is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.
Launch date not confirmedDownloadable