gpt3-finnish-8B-GGML
Based on initial release of FinGPT-3 monolingual GPT-3-like model for Finnish from TurkuNLP Research Group.
This model is quantized GGML format binary of gpt3-finnish-8B.
File | Description |
---|---|
gpt3-finnish-8B.bloomz.ggml.q4_0.bin | 4 bit quantized. For inference using bloomz.cpp |
bloomz.cpp/main -m gpt3-finnish-8B.bloomz.ggml.q4_0.bin -t 4 -n 200 -p "Lasten loru:"
Lasten loru:
Miten monta kärpässilmää,
lakki punainen tai sininen.
Vielä reppukin soma pieni!
Pulkkakin on lautaan tehty.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.