update models

.gitignore

@@ -0,0 +1,2 @@
+.DS_Store
+*~

README.md

@@ -1,52 +1 @@
----
-frameworks:
-- other
-license: other
-tags: []
-tasks:
-- named-entity-recognition
-
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
----
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
-
-SDK下载
-```bash
-#安装ModelScope
-pip install modelscope
-```
-```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('awwaawwa/OneAIFW-Assets')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/awwaawwa/OneAIFW-Assets.git
-```
-
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+# OneAIFW-Assets

hello.json

@@ -0,0 +1,4 @@
+{
+    "hello": "world",
+    "version": "0.3.1"
+}

models/ckiplab/bert-tiny-chinese-ner/config.json

@@ -0,0 +1,178 @@
+{
+  "_name_or_path": "../../../model/bert-tiny-scratch-lm",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "O",
+    "1": "B-CARDINAL",
+    "2": "B-DATE",
+    "3": "B-EVENT",
+    "4": "B-FAC",
+    "5": "B-GPE",
+    "6": "B-LANGUAGE",
+    "7": "B-LAW",
+    "8": "B-LOC",
+    "9": "B-MONEY",
+    "10": "B-NORP",
+    "11": "B-ORDINAL",
+    "12": "B-ORG",
+    "13": "B-PERCENT",
+    "14": "B-PERSON",
+    "15": "B-PRODUCT",
+    "16": "B-QUANTITY",
+    "17": "B-TIME",
+    "18": "B-WORK_OF_ART",
+    "19": "I-CARDINAL",
+    "20": "I-DATE",
+    "21": "I-EVENT",
+    "22": "I-FAC",
+    "23": "I-GPE",
+    "24": "I-LANGUAGE",
+    "25": "I-LAW",
+    "26": "I-LOC",
+    "27": "I-MONEY",
+    "28": "I-NORP",
+    "29": "I-ORDINAL",
+    "30": "I-ORG",
+    "31": "I-PERCENT",
+    "32": "I-PERSON",
+    "33": "I-PRODUCT",
+    "34": "I-QUANTITY",
+    "35": "I-TIME",
+    "36": "I-WORK_OF_ART",
+    "37": "E-CARDINAL",
+    "38": "E-DATE",
+    "39": "E-EVENT",
+    "40": "E-FAC",
+    "41": "E-GPE",
+    "42": "E-LANGUAGE",
+    "43": "E-LAW",
+    "44": "E-LOC",
+    "45": "E-MONEY",
+    "46": "E-NORP",
+    "47": "E-ORDINAL",
+    "48": "E-ORG",
+    "49": "E-PERCENT",
+    "50": "E-PERSON",
+    "51": "E-PRODUCT",
+    "52": "E-QUANTITY",
+    "53": "E-TIME",
+    "54": "E-WORK_OF_ART",
+    "55": "S-CARDINAL",
+    "56": "S-DATE",
+    "57": "S-EVENT",
+    "58": "S-FAC",
+    "59": "S-GPE",
+    "60": "S-LANGUAGE",
+    "61": "S-LAW",
+    "62": "S-LOC",
+    "63": "S-MONEY",
+    "64": "S-NORP",
+    "65": "S-ORDINAL",
+    "66": "S-ORG",
+    "67": "S-PERCENT",
+    "68": "S-PERSON",
+    "69": "S-PRODUCT",
+    "70": "S-QUANTITY",
+    "71": "S-TIME",
+    "72": "S-WORK_OF_ART"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1248,
+  "label2id": {
+    "B-CARDINAL": 1,
+    "B-DATE": 2,
+    "B-EVENT": 3,
+    "B-FAC": 4,
+    "B-GPE": 5,
+    "B-LANGUAGE": 6,
+    "B-LAW": 7,
+    "B-LOC": 8,
+    "B-MONEY": 9,
+    "B-NORP": 10,
+    "B-ORDINAL": 11,
+    "B-ORG": 12,
+    "B-PERCENT": 13,
+    "B-PERSON": 14,
+    "B-PRODUCT": 15,
+    "B-QUANTITY": 16,
+    "B-TIME": 17,
+    "B-WORK_OF_ART": 18,
+    "E-CARDINAL": 37,
+    "E-DATE": 38,
+    "E-EVENT": 39,
+    "E-FAC": 40,
+    "E-GPE": 41,
+    "E-LANGUAGE": 42,
+    "E-LAW": 43,
+    "E-LOC": 44,
+    "E-MONEY": 45,
+    "E-NORP": 46,
+    "E-ORDINAL": 47,
+    "E-ORG": 48,
+    "E-PERCENT": 49,
+    "E-PERSON": 50,
+    "E-PRODUCT": 51,
+    "E-QUANTITY": 52,
+    "E-TIME": 53,
+    "E-WORK_OF_ART": 54,
+    "I-CARDINAL": 19,
+    "I-DATE": 20,
+    "I-EVENT": 21,
+    "I-FAC": 22,
+    "I-GPE": 23,
+    "I-LANGUAGE": 24,
+    "I-LAW": 25,
+    "I-LOC": 26,
+    "I-MONEY": 27,
+    "I-NORP": 28,
+    "I-ORDINAL": 29,
+    "I-ORG": 30,
+    "I-PERCENT": 31,
+    "I-PERSON": 32,
+    "I-PRODUCT": 33,
+    "I-QUANTITY": 34,
+    "I-TIME": 35,
+    "I-WORK_OF_ART": 36,
+    "O": 0,
+    "S-CARDINAL": 55,
+    "S-DATE": 56,
+    "S-EVENT": 57,
+    "S-FAC": 58,
+    "S-GPE": 59,
+    "S-LANGUAGE": 60,
+    "S-LAW": 61,
+    "S-LOC": 62,
+    "S-MONEY": 63,
+    "S-NORP": 64,
+    "S-ORDINAL": 65,
+    "S-ORG": 66,
+    "S-PERCENT": 67,
+    "S-PERSON": 68,
+    "S-PRODUCT": 69,
+    "S-QUANTITY": 70,
+    "S-TIME": 71,
+    "S-WORK_OF_ART": 72
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "pooler_fc_size": 312,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "tokenizer_class": "BertTokenizerFast",
+  "type_vocab_size": 2,
+  "vocab_size": 21128
+}

models/ckiplab/bert-tiny-chinese-ner/onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10da96974bcea16e3b9196346d9533dd1b3caaa1a0f01e9fe29e2cb225b88f32
+size 11705804

models/ckiplab/bert-tiny-chinese-ner/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/ckiplab/bert-tiny-chinese-ner/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizerFast",
+  "unk_token": "[UNK]"
+}

models/funstory-ai/neurobert-mini/config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "B-LOC": 5,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522,
+  "task_specific_params": {
+    "text-classification": {
+      "problem_type": "single_label_classification"
+    }
+  },
+  "finetuning_task": "ner",
+  "name_or_path": "babelner"
+}

models/funstory-ai/neurobert-mini/onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb0eaad7119c5e59212b8e8da722184fffd327c4731bb7e65c2b80d94e5c98a
+size 9656212

models/funstory-ai/neurobert-mini/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/funstory-ai/neurobert-mini/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

wasm/ort-wasm-simd-threaded.wasm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac23f2f3cbd519a65a0796f7c79eb34ead4c1f6f31eb06e14ed8a9579d697ef6
+size 9960821

wasm/ort-wasm-simd.wasm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd07bababc65f53d061f457233eeae501be7ceb8a2adb9eef52d87fe776d865
+size 10014674