Upload quant_config.json with huggingface_hub
Browse files- quant_config.json +9 -0
quant_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"zero_point": true,
|
| 3 |
+
"q_group_size": 128,
|
| 4 |
+
"w_bit": 4,
|
| 5 |
+
"version": "GEMM",
|
| 6 |
+
"modules_to_not_convert": [
|
| 7 |
+
"gate"
|
| 8 |
+
]
|
| 9 |
+
}
|