Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "MoritzLaurer/ernie-m-large-mnli-xnli",
+  "act_dropout": 0.0,
+  "architectures": [
+    "ErnieMForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "ernie_m",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "paddlenlp_version": null,
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 16,
+  "vocab_size": 250002
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d59f6bbd796cc2a89aa4d9bfa758074ccfe25597ef4b6fc18a96da86e1d944
+size 596082

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9ab0362121f3d501a0393480345b0bec43646e1bc416638b93e69584684fc6
+size 2239569920

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe9aa46100f420456251f2207b1189105c16ed29d6a03bc3524366d8bfe442e
+size 1202073528

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a066b5eb6c9bf1ed5f4ec868ba0f933ac76783879fbda4167cbd4b9f1afbe10
+size 562905520

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4399c549cdaa90f54d720dfc24ba36b55b6bbe1a43a29c6984de335f28b9426a
+size 1220946720

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a066b5eb6c9bf1ed5f4ec868ba0f933ac76783879fbda4167cbd4b9f1afbe10
+size 562905520

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e820c89f8d189c3b1e38af9b25e43e018e76740be29cc8920a496a3ec462424
+size 562905519

quantize_config.json

@@ -0,0 +1,110 @@
+{
+    "q8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "CumSum",
+                    "Div",
+                    "Erf",
+                    "Gather",
+                    "Gemm",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Tanh",
+                    "Transpose",
+                    "Unsqueeze"
+                ],
+                "weight_type": "QInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "int8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "CumSum",
+                    "Div",
+                    "Erf",
+                    "Gather",
+                    "Gemm",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Tanh",
+                    "Transpose",
+                    "Unsqueeze"
+                ],
+                "weight_type": "QInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "uint8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "CumSum",
+                    "Div",
+                    "Erf",
+                    "Gather",
+                    "Gemm",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Tanh",
+                    "Transpose",
+                    "Unsqueeze"
+                ],
+                "weight_type": "QUInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "q4": {
+        "block_size": 32,
+        "is_symmetric": true,
+        "accuracy_level": null
+    },
+    "bnb4": {
+        "block_size": 64,
+        "quant_type": 1
+    }
+}

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 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "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": "[SEP]",
+      "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": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "encoding": "utf8",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "ErnieMTokenizer",
+  "unk_token": "[UNK]"
+}