Upload fp16/q4f16 decoder ONNX weights w/ float32 inputs_embeds (#15)
Browse files- Upload q4f16 decoder ONNX weights w/ float32 inputs_embeds (792b8092e2787477ebc2678ab2b3c58b93623baa)
- Upload fp16 decoder ONNX weights w/ float32 inputs_embeds (6847a1ceb4ae2a8516715a4df0ccf43e17538e57)
onnx/decoder_model_merged_fp16.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6ec36a518b896dfc6448c4343898d0ea5109702677d34cea3919fba074044d1
|
3 |
+
size 1342510427
|
onnx/decoder_model_merged_q4f16.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d74ec46083829ddb18f58fcceb358d2ba58d2a1320bdab431c32e4d2896981d
|
3 |
+
size 965031477
|