A quantized version of Llama-3.1-8B-Instruct. The model was quantized using AutoAWQ with biomedical question-answering (QA) data as calibration.
1quant_config = {
2 "zero_point": True,
3 "q_group_size": 128,
4 "w_bit": 4,
5 "version": "GEMM"
6}
The model follows the license of the base Llama-3.1-8B-Instruct model.