[work in progress] Upload optimized language model w/ WebGPU-compatible GQA
#9
by
Xenova
HF Staff
- opened
- onnx/decoder_model_merged.onnx +2 -2
- onnx/decoder_model_merged_bnb4.onnx +2 -2
- onnx/decoder_model_merged_fp16.onnx +2 -2
- onnx/decoder_model_merged_int8.onnx +2 -2
- onnx/decoder_model_merged_q4.onnx +2 -2
- onnx/decoder_model_merged_q4f16.onnx +2 -2
- onnx/decoder_model_merged_quantized.onnx +2 -2
- onnx/decoder_model_merged_uint8.onnx +2 -2
onnx/decoder_model_merged.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 sha256:33864f9d40aaa945d966d2bed2a5b17f30ad800ab11729d76d33dc450ea86e86
|
3 |
+
size 1450073926
|
onnx/decoder_model_merged_bnb4.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:bd7b13ab526cbc87914acc69b19538aff6cc0c15219bd45b702fd6eb18f6e4e7
|
3 |
+
size 206151457
|
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:b56d17c9751f513a41f4a8c9df5f47b9e8efe144bdb7a8d7ff1a606c454775d5
|
3 |
+
size 725137331
|
onnx/decoder_model_merged_int8.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 sha256:1dd1d97f5ce7085eb5c6376a1e3269533aada7872435f8583babe89070c87740
|
3 |
+
size 364687373
|
onnx/decoder_model_merged_q4.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 sha256:9690cc2021147bf526d8283c35794db8fb50da7a7c38d25dcf74f602f4d0b112
|
3 |
+
size 228767321
|
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:c5ec826210aadb606bc0df1839cee7f3f02edaa5f0e0fa4dce579e8024eaf6f0
|
3 |
+
size 204976454
|
onnx/decoder_model_merged_quantized.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 sha256:86fcfd6e3d57ea74273c12b7a4e3f4d5995196bad5001199ca7b36a587369f3a
|
3 |
+
size 364687494
|
onnx/decoder_model_merged_uint8.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 sha256:86fcfd6e3d57ea74273c12b7a4e3f4d5995196bad5001199ca7b36a587369f3a
|
3 |
+
size 364687494
|