InferenceIllusionist / Llama3-ChatQA-1.5-8B-iMat-GGUF

Quantized from fp16. Weighted quantizations were creating using fp16 GGUF and groupsmerged-enhancedV2-TurboMini.txt in 234 chunks and nctx=512 This method of calculating the importance matrix showed improvements in some areas for Mistral 7b and Llama3 8b models, see above post…