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-xbase-zh",
+  "architectures": [
+    "ErnieForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "ernie",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 20,
+  "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 sha256:8785b6ed4c2ae65a68bdc74a0eb6141fb1a9c3897dc210c1fb6ea0bb2861361b
+size 1184848195

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cdac434f09ee702c818e6a6e491f137947c3a3f0bfb6e731a10101cb3ae014
+size 316187530

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db792d7946906674ee4b5e5eade5cb694738b82b36bf060d1d2f1e33ac93e0d
+size 592803695

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed53d630d725eb860d3832dd7990e52fdcf8f9639f2461ee98722f7fda74baa5
+size 298728837

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f869975e158babb8cc100c332f4ea7d8c67dc221210a638c3e68dae0c142ec5
+size 331980718

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed53d630d725eb860d3832dd7990e52fdcf8f9639f2461ee98722f7fda74baa5
+size 298728837

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c1abd5272e3694d9f7e2f51ffe42e59b040fe9a52ab7fc089ef0aac8a01794
+size 298728834

quantize_config.json

@@ -0,0 +1,105 @@
+{
+    "fp16": {},
+    "q8": {
+        "per_model_config": {
+            "model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Erf",
+                    "Gather",
+                    "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",
+                    "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",
+                    "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]"
+}