elloza commited on
Commit
a026303
·
1 Parent(s): e2141cd

Added quantized

Browse files
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a40e904daff4520b02596ef8b86f2d60ea1dcb4a46f0c9cb5b0a39e45c050da
3
+ size 111182784
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81710ae845d7bd8a0828c861289b3daf60a69c981c63ee3faa06889a1b9f7087
3
+ size 58085640
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48965014a5f30797d4c8bc8cdb80c43334a251e12eaf56f2a1d928adccef7d54
3
+ size 38318071
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7d65f248108861a8d93479fb013093ed1ff42accbc73b540f287848be15f67
3
+ size 111237888
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c6138f1c814e124a0e8c24e6ae6ca3f0e82b02232274ac15316c58049c68f8
3
+ size 56815300
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec9fa3ef32288d446ce0a5d61a7ae0a4c6d2b9f89c329a0d4524651aa41c2a3
3
+ size 38318071
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec9fa3ef32288d446ce0a5d61a7ae0a4c6d2b9f89c329a0d4524651aa41c2a3
3
+ size 38318071
quantize_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modes": [
3
+ "fp16",
4
+ "q8",
5
+ "int8",
6
+ "uint8",
7
+ "q4",
8
+ "q4f16",
9
+ "bnb4"
10
+ ],
11
+ "per_channel": true,
12
+ "reduce_range": true,
13
+ "block_size": null,
14
+ "is_symmetric": true,
15
+ "accuracy_level": null,
16
+ "quant_type": 1,
17
+ "op_block_list": null
18
+ }