README.md

metadata

base_model:
  - anthracite-org/magnum-v3-34b
pipeline_tag: text-generation
tags:
  - awq
  - text-generation-inference

Model Details

This is a AWQ GEMM quant of magnum-v3-34b: https://huggingface.co/anthracite-org/magnum-v3-34b

Model Description

Model has been quantized on 6xRTX4090, here are quantization parameters:

"zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM"