Quantization made by Richard Erkhov.
This model is a fine-tuned version of
PygmalionAI/pygmalion-350m on a 2.4MB dataset.
It achieves the following results on the evaluation set:
A proof-of-concept model based on PygmalionAI/pygmalion-350m, which was in turn based on OPT-350m.
This model was fine-tuned purely for testing purposes.
