Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[UNK]": 39979
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "nghuyong/ernie-3.0-medium-zh",
+  "architectures": [
+    "ErnieForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "ernie",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "task_type_vocab_size": 16,
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 4,
+  "use_cache": true,
+  "use_task_id": true,
+  "vocab_size": 40000
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3074d4f05ef2f34a3ab316745322ccddf9800fe715a68a469881543f3134304c
+size 302030872

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e0b0a4e6162195e2cdcd6a5985e8ebcd12da5bfdd34f340fe80334721f804f
+size 154027603

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ad337db36b467915851093fc4a00e0c45a6a0acc157718749d987db0e8bbd1
+size 151141098

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72eb7f40217e4c483672657953c4e5852ce6a0eaa6252f414945352f9489f6fb
+size 76242841

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bde9b3e15399fd99501167b761361715f35e3c13ee0c41da90c9a38db2d6dfd
+size 156718404

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72eb7f40217e4c483672657953c4e5852ce6a0eaa6252f414945352f9489f6fb
+size 76242841

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52eb53fa636819d52acfed09a88bf432fd953a03549f234b9fe1002d13c1899c
+size 76242839

quantize_config.json

@@ -0,0 +1,108 @@
+{
+    "fp16": {},
+    "q8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Erf",
+                    "Gather",
+                    "Identity",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze"
+                ],
+                "weight_type": "QInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "int8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Erf",
+                    "Gather",
+                    "Identity",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze"
+                ],
+                "weight_type": "QInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "uint8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Erf",
+                    "Gather",
+                    "Identity",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "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
+    }
+}

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "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": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39979": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}