Update hf_quant_config.json
Browse files- hf_quant_config.json +1 -1
hf_quant_config.json
CHANGED
|
@@ -5,8 +5,8 @@
|
|
| 5 |
},
|
| 6 |
"quantization": {
|
| 7 |
"quant_algo": "NVFP4",
|
| 8 |
-
"kv_cache_quant_algo": "FP8",
|
| 9 |
"group_size": 16,
|
|
|
|
| 10 |
"exclude_modules": [
|
| 11 |
"lm_head"
|
| 12 |
]
|
|
|
|
| 5 |
},
|
| 6 |
"quantization": {
|
| 7 |
"quant_algo": "NVFP4",
|
|
|
|
| 8 |
"group_size": 16,
|
| 9 |
+
"kv_cache_quant_algo": "FP8",
|
| 10 |
"exclude_modules": [
|
| 11 |
"lm_head"
|
| 12 |
]
|