Llama-2-7B-Chat-AWQ/quant_config.json at 181ecf99f0218f3d6408532d8f56acf8bbccbdb3 - Llama-2-7B-Chat-AWQ - Gitea: Git with a cup of tea

6 lines

90 B

JSON

Raw Blame History

 {
     "zero_point": true,
     "q_group_size": 128,
     "w_bit": 4,
     "version": "GEMM"
 }