Compatibility warning: these are ik_llama.cpp GGUF quantizations. They are intended for ikawrakow/ik_llama.cpp, not standard mainline llama.cpp.

For regular llama.cpp-compatible GGUFs, use KeinNiemand/Kuwutu-7B-CYOA-GGUF.

This repository contains IK-specific GGUF quantizations of KeinNiemand/Kuwutu-7B-CYOA, a narrow fine-tune of Mawdistical/Kuwutu-7B for adult furry CYOA / interactive-fiction style continuation.

Important Replacement Notice

Older GGUF files in this repository named like run0067-checkpoint-274-*.gguf were generated with incorrect RoPE metadata and should be considered broken. In particular, those exports could load with qwen2.rope.freq_base / freq_base_train set to 10000 instead of the correct 640000, causing severe generation degradation.

Use the Kuwutu-7B-CYOA-*.gguf files instead. The corrected files should report qwen2.rope.freq_base = 640000 when loaded.

Other Versions

Canonical LoRA adapter: KeinNiemand/Kuwutu-7B-CYOA-LoRA
Merged HF model: KeinNiemand/Kuwutu-7B-CYOA
Adapter GGUF: KeinNiemand/Kuwutu-7B-CYOA-LoRA-GGUF
Mainline-compatible merged GGUF: KeinNiemand/Kuwutu-7B-CYOA-GGUF

Files

Kuwutu-7B-CYOA-IQ6_K.gguf
Kuwutu-7B-CYOA-IQ5_K.gguf
Kuwutu-7B-CYOA-IQ5_KS.gguf
Kuwutu-7B-CYOA-IQ4_K.gguf
Kuwutu-7B-CYOA-IQ4_KS.gguf
Kuwutu-7B-CYOA-IQ4_KSS.gguf
Kuwutu-7B-CYOA-IQ3_K.gguf
Kuwutu-7B-CYOA-IQ2_KL.gguf

Model Summary

This is a narrow adult furry CYOA / interactive-fiction model. It is not intended as a general writing model or broad instruction model.

The training data is permissioned adult furry CYOA / interactive-fiction writing. The dataset is not redistributed here.

Quantization Notes

These quants were produced from the merged model using an imatrix generated from project calibration text. They have not been formally benchmarked beyond local sanity checks.

KeinNiemand/Kuwutu-7B-CYOA-IK-GGUF

Kuwutu-7B-CYOA-IK-GGUF

Important Replacement Notice

Other Versions

Files

Model Summary

Quantization Notes

KeinNiemand/
Kuwutu-7B-CYOA-IK-GGUF