GGUF importance matrix (imatrix) quants for https://huggingface.co/jondurbin/bagel-dpo-20b-v04-llama
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

Layers	Context	Template
48	32768	[INST] <<SYS>> {instructions} <</SYS>> {prompt} [/INST] {response}

GGUF

Model size

19.9B params

Architecture

llama

2-bit

3-bit

4-bit

8-bit

16-bit

Inference Examples

Inference API (serverless) does not yet support gguf models for this pipeline type.