Edit model card

GGUF importance matrix (imatrix) quants for https://huggingface.co/ibivibiv/alpaca-dragon-72b-v1
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

Layers	Context	Template
80	32768	### Instruction: {prompt} ### Response: {response}

GGUF

Model size

72.3B params

Architecture

llama

2-bit

3-bit

4-bit

Inference Examples

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