dranger003/CausalLM-34b-beta-iMat.GGUF

GGUF importance matrix (imatrix) quants for https://huggingface.co/CausalLM/34b-beta
The importance matrix was trained for 40K tokens (80 batches of 512 tokens) using random data.

From the model author:
Please do not use wikitext for quantization calibration because all wikitext have been re-aligned on synthetic dataset, and its distribution differs significantly from the original wikitext.

Layers	Context	Template
60	200000	<|im_start|>system {instructions}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant {response}