Files
neural-chat-7B-v3-3-wizardm…/quant_config.json
2025-02-01 02:29:51 +08:00

7 lines
126 B
JSON

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