GGUF importance matrix (imatrix) quants for https://huggingface.co/jondurbin/bagel-34b-v0.4
The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.

Feb. 21, 2024: Updating quants from latest commit.

Layers	Context	Template
60	200000	[INST] <<SYS>> {instructions} <</SYS>> {prompt} [/INST] {response}

GGUF

Model size

34.4B params

Architecture

llama

1-bit

2-bit

3-bit

4-bit

8-bit

Inference Examples

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