Florian commited on
Commit
1347818
1 Parent(s): 021f797

initial commit

Browse files
.gitattributes CHANGED
@@ -33,4 +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
36
- *.md 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,55 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:98b45ea81164d1e1a1dd82255207053b15cd6c69d922a1c5cf3387ce604d4b74
3
- size 28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ https://huggingface.co/nreimers/mmarco-mMiniLMv2-L6-H384-v1
2
+
3
+ optimized with onnx o4
4
+
5
+ ```
6
+ from pathlib import Path
7
+ from transformers import AutoTokenizer
8
+ from optimum.onnxruntime import ORTModelForSequenceClassification, ORTOptimizer
9
+ from optimum.onnxruntime import AutoOptimizationConfig
10
+
11
+ model = "nreimers/mmarco-mMiniLMv2-L6-H384-v1"
12
+ tokenizer = AutoTokenizer.from_pretrained(model)
13
+ ort_model = ORTModelForSequenceClassification.from_pretrained(model, export=True)
14
+
15
+ save_dir = Path("/tmp/optimized_models")
16
+ save_dir.mkdir(exist_ok=True, parents=True)
17
+
18
+ optimizer = ORTOptimizer.from_pretrained(ort_model)
19
+ optimizer.optimize(
20
+ optimization_config=AutoOptimizationConfig.O4(),
21
+ save_dir=save_dir,
22
+ )
23
+ ```
24
+
25
+ Run it with onnx
26
+
27
+ ```
28
+ import torch
29
+ from transformers import AutoTokenizer
30
+ from transformers.pipelines.text_classification import ClassificationFunction
31
+ from optimum.pipelines import pipeline as ort_pipeline
32
+ from optimum.onnxruntime import ORTModelForSequenceClassification
33
+
34
+
35
+ model = "Slite/mmarco-mMiniLMv2-L6-H384-v1-onnx-o4"
36
+ device = torch.device(0) if torch.cuda.is_available() else -1
37
+ tokenizer = AutoTokenizer.from_pretrained(model)
38
+ ort_model = ORTModelForSequenceClassification.from_pretrained(
39
+ model, file_name="model_optimized.onnx")
40
+ cross_encoder = ort_pipeline(
41
+ task="text-classification",
42
+ model=ort_model,
43
+ tokenizer=tokenizer,
44
+ device=device,
45
+ function_to_apply=ClassificationFunction.SIGMOID,
46
+ padding=True,
47
+ truncation=True)
48
+
49
+ cross_encoder([{
50
+ "text":
51
+ "Quel est le but de la vie ?",
52
+ "text_pair":
53
+ "Le but de la vie est une question subjective et dépend de la croyance et de la perspective personnelle de chaque individu. Pour certains, le but peut être de trouver la bonheur et le contentement personnel, pour d'autres cela peut être de faire une différence positive dans le monde, de vivre en harmonie avec les autres, de découvrir la signification et le propre but de leur existence, entre autres. En fin de compte, le but de la vie est déterminé par chaque individu eux-mêmes."
54
+ }])
55
+ ```
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nreimers/mmarco-mMiniLMv2-L6-H384-v1",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 384,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1536,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 514,
23
+ "model_type": "xlm-roberta",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 6,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.35.2",
30
+ "type_vocab_size": 1,
31
+ "use_cache": true,
32
+ "vocab_size": 250002
33
+ }
model_optimized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eaae91d96a80ccd9af77c8cd0ab7c5b799c8aa9180ed83b8b4528311a812660
3
+ size 214017536
ort_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {
5
+ "disable_attention": null,
6
+ "disable_attention_fusion": false,
7
+ "disable_bias_gelu": null,
8
+ "disable_bias_gelu_fusion": false,
9
+ "disable_bias_skip_layer_norm": null,
10
+ "disable_bias_skip_layer_norm_fusion": false,
11
+ "disable_embed_layer_norm": true,
12
+ "disable_embed_layer_norm_fusion": true,
13
+ "disable_gelu": null,
14
+ "disable_gelu_fusion": false,
15
+ "disable_group_norm_fusion": true,
16
+ "disable_layer_norm": null,
17
+ "disable_layer_norm_fusion": false,
18
+ "disable_packed_kv": true,
19
+ "disable_rotary_embeddings": false,
20
+ "disable_shape_inference": false,
21
+ "disable_skip_layer_norm": null,
22
+ "disable_skip_layer_norm_fusion": false,
23
+ "enable_gelu_approximation": true,
24
+ "enable_gemm_fast_gelu_fusion": false,
25
+ "enable_transformers_specific_optimizations": true,
26
+ "fp16": true,
27
+ "no_attention_mask": false,
28
+ "optimization_level": 2,
29
+ "optimize_for_gpu": true,
30
+ "optimize_with_onnxruntime_only": null,
31
+ "use_mask_index": false,
32
+ "use_multi_head_attention": false,
33
+ "use_raw_attention_mask": false
34
+ },
35
+ "optimum_version": "1.14.1",
36
+ "quantization": {},
37
+ "transformers_version": "4.35.2",
38
+ "use_external_data_format": false
39
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
+ size 17082756
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }