dranger003/CodeFuse-DeepSeek-33B-iMat.GGUF

GGUF importance matrix (imatrix) quants for https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B

• The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.
• The imatrix is being used on the K-quants as well.

Layers	Context	Template
62	16384	<s>system {instructions} <s>human {prompt} <s>bot {response}<｜end▁of▁sentence｜>