Edit model card

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.

Downloads last month
0
Inference Examples
Unable to determine this model's library. Check the docs .