dranger003
/

bagel-34b-v0.4-iMat.GGUF

Text Generation

Model card Files Files and versions

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.

Prompt strategies: https://huggingface.co/jondurbin/bagel-34b-v0.4#prompting-strategies

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

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

Downloads last month: 45

GGUF

Model size

34B params

Architecture

llama

Hardware compatibility

Log In to add your hardware

1-bit

2-bit

3-bit

4-bit

8-bit