Upload quantize_config.json with huggingface_hub
Browse files- quantize_config.json +18 -0
quantize_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"modes": [
|
| 3 |
+
"fp16",
|
| 4 |
+
"q8",
|
| 5 |
+
"int8",
|
| 6 |
+
"uint8",
|
| 7 |
+
"q4",
|
| 8 |
+
"q4f16",
|
| 9 |
+
"bnb4"
|
| 10 |
+
],
|
| 11 |
+
"per_channel": true,
|
| 12 |
+
"reduce_range": true,
|
| 13 |
+
"block_size": null,
|
| 14 |
+
"is_symmetric": true,
|
| 15 |
+
"accuracy_level": null,
|
| 16 |
+
"quant_type": 1,
|
| 17 |
+
"op_block_list": null
|
| 18 |
+
}
|