Mistral-Nemo-Instruct-12B-iMat-GGUF

Important Note: Inferencing is only available on this fork of llama.cpp at the moment: https://github.com/iamlemec/llama.cpp/tree/mistral-nemo (All credits to iamlemec for his work on Mistral-Nemo support) Other front-ends like the main branch of llama.cpp, kobold.cpp, and text-generation-web-ui may not work as intended

Quantized from Mistral-Nemo-Instruct-2407 fp16

• Weighted quantizations were creating using fp16 GGUF and groups_merged.txt in 92 chunks and n_ctx=512
• Static fp16 will also be included in repo
• For a brief rundown of iMatrix quant performance please see this PR
• All quants are verified working prior to uploading to repo for your safety and convenience

KL-Divergence Reference Chart (Click on image to view in full size)

Quant-specific Tips:

• If you are getting a cudaMalloc failed: out of memory error, try passing an argument for lower context in llama.cpp, e.g. for 8k: -c 8192
• If you have all ampere generation or newer cards, you can use flash attention like so: -fa
• Provided Flash Attention is enabled you can also use quantized cache to save on VRAM e.g. for 8-bit: -ctk q8_0 -ctv q8_0
• Mistral recommends a temperature of 0.3 for this model

Original model card can be found here