Outdated:
Outdaded tokenizer configuration!
This is only kept for historical purposes, use the newer models instead of this one.For example, use version 0.72 instead.
This is a Llama-3 land now, cowboys!
This is an atempt at a less censored Llama-3.
GGUF-IQ-Imatrix quants for Nitral-AI/Poppy_Porpoise-v0.2-L3-8B.
Recommended presets here or here.
Use the latest version of KoboldCpp. Use the provided presets.
This is all still highly experimental, modified configs were used to avoid the tokenizer issues, let the authors know how it performs for you, feedback is more important than ever now.
Original model information:
