gghfez/gemma-2-27b-rp-c2-GGUF

GGUF quants of gghfez/gemma-2-27b-rp-c2

Seems to work pretty well with SillyTavern

Prompting

Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:

<|im_start|>user Hi there!<|im_end|> <|im_start|>assistant Nice to meet you!<|im_end|> <|im_start|>user Can I ask a question?<|im_end|> <|im_start|>assistant

Training:

Trained on a subset of the synthetic RP dataset from: Sao10K/c2-Logs-Filtered