Hugging Face's logo

shoibl
/
phi2_onnx

Text Generation
Transformers
ONNX
phi
custom_code
Model card Files
xet
 Community
shoibl commited on
Commit
24b1304
·
verified ·
1 Parent(s): 787959a

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. _model_layers.0_self_attn_rotary_emb_Constant_4_attr__value +0 -0
  3. _model_layers.0_self_attn_rotary_emb_Constant_attr__value +0 -0
  4. config.json +1 -1
  5. generation_config.json +6 -0
  6. onnx/model.onnx +3 -0
  7. onnx/model.onnx_data +3 -0
  8. onnx/model_quantized.onnx +3 -0
  9. quantize_config.json +38 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
_model_layers.0_self_attn_rotary_emb_Constant_4_attr__value ADDED
Binary file (262 kB). View file
 
_model_layers.0_self_attn_rotary_emb_Constant_attr__value ADDED
Binary file (262 kB). View file
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "roberta_base_qa_onnx",
3
  "architectures": [
4
  "PhiForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "microsoft/phi-2",
3
  "architectures": [
4
  "PhiForCausalLM"
5
  ],
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.37.2"
6
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed32f3280929a5a355b44d4fb2e42a38fbcd3d58ea769b044af4d360774fd1f
3
+ size 1628979
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b530fa988b74eee7a9a874998f95ea2e5bf2dfe4bccf6eb62b2255997fd33418
3
+ size 22237470720
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb904a32b7edfe037e89206228d729ccc0a46395476a96de38f3d7bf7909e8a5
3
+ size 2784697161
quantize_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Sub",
8
+ "Cast",
9
+ "Less",
10
+ "Add",
11
+ "ConstantOfShape",
12
+ "Concat",
13
+ "Reshape",
14
+ "Mul",
15
+ "MatMul",
16
+ "Shape",
17
+ "ReduceMean",
18
+ "Slice",
19
+ "Softmax",
20
+ "Neg",
21
+ "Transpose",
22
+ "Div",
23
+ "Where",
24
+ "Range",
25
+ "Unsqueeze",
26
+ "Squeeze",
27
+ "Equal",
28
+ "Gather",
29
+ "Pow",
30
+ "Tanh",
31
+ "Sqrt",
32
+ "Expand",
33
+ "Constant"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ }
37
+ }
38
+ }