rocca commited on
Commit
773d3eb
1 Parent(s): f4d9847

Upload ORT format for 430m model

Browse files
.gitattributes CHANGED
@@ -29,3 +29,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ 430m/rwkv-4-pile-430m-uint8.ort filter=lfs diff=lfs merge=lfs -text
33
+ 430m/rwkv-4-pile-430m-uint8.with_runtime_opt.ort filter=lfs diff=lfs merge=lfs -text
34
+ 430m/rwkv-4-pile-430m.ort filter=lfs diff=lfs merge=lfs -text
35
+ 430m/rwkv-4-pile-430m.with_runtime_opt.ort filter=lfs diff=lfs merge=lfs -text
430m/rwkv-4-pile-430m-uint8.ort ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87993b731797c9163a18ca5283fb636c134b54626e38959d4fe0825d26b47b71
3
+ size 437061704
430m/rwkv-4-pile-430m-uint8.required_operators.config ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ # Generated from model/s:
2
+ # - /content/RWKV-LM/RWKV-v4/rwkv-uint8.ort
3
+ ai.onnx;1;LayerNormalization
4
+ ai.onnx;11;DynamicQuantizeLinear
5
+ ai.onnx;13;Concat,DequantizeLinear,Exp,Gather,Max,Sigmoid,Unsqueeze
6
+ ai.onnx;14;Add,Div,Mul,Relu,Sub
7
+ com.microsoft;1;MatMulIntegerToFloat
430m/rwkv-4-pile-430m-uint8.required_operators.with_runtime_opt.config ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ # Generated from model/s:
2
+ # - /content/RWKV-LM/RWKV-v4/rwkv-uint8.with_runtime_opt.ort
3
+ # - /content/RWKV-LM/RWKV-v4/tmpkudq58_8.without_runtime_opt/rwkv-uint8.ort
4
+ ai.onnx;10;MatMulInteger
5
+ ai.onnx;11;DynamicQuantizeLinear
6
+ ai.onnx;13;Cast,Concat,DequantizeLinear,Exp,Gather,Max,Pow,ReduceMean,Sigmoid,Sqrt,Unsqueeze
7
+ ai.onnx;14;Add,Div,Mul,Relu,Sub
430m/rwkv-4-pile-430m-uint8.with_runtime_opt.ort ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338af68cf14dec59c64544a66d5a13533a3ef4823fc162908473604febb28786
3
+ size 438774216
430m/rwkv-4-pile-430m.ort ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed6b7d9e5b9805b4c53aefffa00533a66fe4b0a1406e9cee7124914852e42ef6
3
+ size 1727793456
430m/rwkv-4-pile-430m.required_operators.config ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ # Generated from model/s:
2
+ # - /content/RWKV-LM/RWKV-v4/rwkv.ort
3
+ ai.onnx;1;LayerNormalization
4
+ ai.onnx;13;Concat,Exp,Gather,MatMul,Max,Sigmoid,Unsqueeze
5
+ ai.onnx;14;Add,Div,Mul,Relu,Sub
430m/rwkv-4-pile-430m.required_operators.with_runtime_opt.config ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ # Generated from model/s:
2
+ # - /content/RWKV-LM/RWKV-v4/rwkv.with_runtime_opt.ort
3
+ # - /content/RWKV-LM/RWKV-v4/tmpjyhbv_6_.without_runtime_opt/rwkv.ort
4
+ ai.onnx;13;Concat,Exp,Gather,MatMul,Max,Pow,ReduceMean,Sigmoid,Sqrt,Unsqueeze
5
+ ai.onnx;14;Add,Div,Mul,Relu,Sub
430m/rwkv-4-pile-430m.with_runtime_opt.ort ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79113d0ebfc391a3598b9ebe3d22bb03ec7413f71234be66f4811b08a46f37f1
3
+ size 1729404824