dranger003/Nous-Capybara-34B-iMat.GGUF

GGUF importance matrix (imatrix) quants for https://huggingface.co/NousResearch/Nous-Capybara-34B
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

Although this model is quite good, it is very sensitive with its prompt template - no space at end after ASSISTANT:

Layers	Context	Template
60	200000	USER: {prompt} ASSISTANT:{response}