initial commit

.gitattributes

@@ -33,4 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-*.md filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,55 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:98b45ea81164d1e1a1dd82255207053b15cd6c69d922a1c5cf3387ce604d4b74
-size 28
+https://huggingface.co/nreimers/mmarco-mMiniLMv2-L6-H384-v1
+
+optimized with onnx o4
+
+```
+from pathlib import Path
+from transformers import AutoTokenizer
+from optimum.onnxruntime import ORTModelForSequenceClassification, ORTOptimizer
+from optimum.onnxruntime import AutoOptimizationConfig
+
+model = "nreimers/mmarco-mMiniLMv2-L6-H384-v1"
+tokenizer = AutoTokenizer.from_pretrained(model)
+ort_model = ORTModelForSequenceClassification.from_pretrained(model, export=True)
+
+save_dir = Path("/tmp/optimized_models")
+save_dir.mkdir(exist_ok=True, parents=True)
+
+optimizer = ORTOptimizer.from_pretrained(ort_model)
+optimizer.optimize(
+    optimization_config=AutoOptimizationConfig.O4(),
+    save_dir=save_dir,
+)
+```
+
+Run it with onnx
+
+```
+import torch
+from transformers import AutoTokenizer
+from transformers.pipelines.text_classification import ClassificationFunction
+from optimum.pipelines import pipeline as ort_pipeline
+from optimum.onnxruntime import ORTModelForSequenceClassification
+
+
+model = "Slite/mmarco-mMiniLMv2-L6-H384-v1-onnx-o4"
+device = torch.device(0) if torch.cuda.is_available() else -1
+tokenizer = AutoTokenizer.from_pretrained(model)
+ort_model = ORTModelForSequenceClassification.from_pretrained(
+    model, file_name="model_optimized.onnx")
+cross_encoder = ort_pipeline(
+    task="text-classification",
+    model=ort_model,
+    tokenizer=tokenizer,
+    device=device,
+    function_to_apply=ClassificationFunction.SIGMOID,
+    padding=True,
+    truncation=True)
+
+cross_encoder([{
+    "text":
+    "Quel est le but de la vie ?",
+    "text_pair":
+    "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."
+}])
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "nreimers/mmarco-mMiniLMv2-L6-H384-v1",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model_optimized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eaae91d96a80ccd9af77c8cd0ab7c5b799c8aa9180ed83b8b4528311a812660
+size 214017536

ort_config.json

@@ -0,0 +1,39 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {
+    "disable_attention": null,
+    "disable_attention_fusion": false,
+    "disable_bias_gelu": null,
+    "disable_bias_gelu_fusion": false,
+    "disable_bias_skip_layer_norm": null,
+    "disable_bias_skip_layer_norm_fusion": false,
+    "disable_embed_layer_norm": true,
+    "disable_embed_layer_norm_fusion": true,
+    "disable_gelu": null,
+    "disable_gelu_fusion": false,
+    "disable_group_norm_fusion": true,
+    "disable_layer_norm": null,
+    "disable_layer_norm_fusion": false,
+    "disable_packed_kv": true,
+    "disable_rotary_embeddings": false,
+    "disable_shape_inference": false,
+    "disable_skip_layer_norm": null,
+    "disable_skip_layer_norm_fusion": false,
+    "enable_gelu_approximation": true,
+    "enable_gemm_fast_gelu_fusion": false,
+    "enable_transformers_specific_optimizations": true,
+    "fp16": true,
+    "no_attention_mask": false,
+    "optimization_level": 2,
+    "optimize_for_gpu": true,
+    "optimize_with_onnxruntime_only": null,
+    "use_mask_index": false,
+    "use_multi_head_attention": false,
+    "use_raw_attention_mask": false
+  },
+  "optimum_version": "1.14.1",
+  "quantization": {},
+  "transformers_version": "4.35.2",
+  "use_external_data_format": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
+size 17082756

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}