GGUF importance matrix (imatrix) quants for https://huggingface.co/152334H/miqu-1-70b-sf
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

These quants are based off the second dequantization by 152334H.

Layers	Context	Template
80	32764	<s> [INST] {prompt} [/INST] {response}

Downloads last month: 14

GGUF

Model size

69B params

Architecture

llama

2-bit

3-bit

4-bit

Text Generation

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