dranger003/Qwen1.5-72B-Chat-iMat.GGUF

NOTE: You will need a recent build of llama.cpp to run these quants (i.e. at least commit 494c870).

2024-03-19: Uploading new quants retrained on wiki.train.raw for ~100K tokens.
2024-03-07: Refreshing quants using latest build as things seem to have stabilized a bit now.

GGUF importance matrix (imatrix) quants for https://huggingface.co/Qwen/Qwen1.5-72B-Chat

• 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
80	32768	<|im_start|>system {instructions}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant {response}