Upload FP8 quantized ONNX model
Browse files- .gitattributes +1 -0
- model_fp8.onnx +3 -0
- model_fp8.onnx.data +3 -0
.gitattributes
CHANGED
|
@@ -41,3 +41,4 @@ model_h100_bf16.plan filter=lfs diff=lfs merge=lfs -text
|
|
| 41 |
model_rtx_pro_6000_bf16.plan filter=lfs diff=lfs merge=lfs -text
|
| 42 |
model_rtx_pro_6000_fp8.plan filter=lfs diff=lfs merge=lfs -text
|
| 43 |
model_l40s_fp8.plan filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 41 |
model_rtx_pro_6000_bf16.plan filter=lfs diff=lfs merge=lfs -text
|
| 42 |
model_rtx_pro_6000_fp8.plan filter=lfs diff=lfs merge=lfs -text
|
| 43 |
model_l40s_fp8.plan filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
model_fp8.onnx.data filter=lfs diff=lfs merge=lfs -text
|
model_fp8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ccd3ab6eff021d4f3ddab1f08b778e21cea57b55d1ee48312d911fcc93d67c9
|
| 3 |
+
size 2231215
|
model_fp8.onnx.data
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30d9a6d4c6e6a49353a16341d1f91aeceb8bc2a354da8b27bdac1eb190adf14b
|
| 3 |
+
size 3999557632
|