初始化项目，由ModelHub XC社区提供模型

Model: LLukas22/bert-base-uncased-embedding-step-scheduler
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

.gitignore

@@ -0,0 +1,3 @@
+checkpoints/
+checkpoint-*/
+runs/

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,76 @@
+---
+license: cc-by-nc-4.0
+pipeline_tag: sentence-similarity
+tags:
+    - sentence-transformers
+    - feature-extraction
+    - sentence-similarity
+    - transformers
+    - generated_from_trainer
+datasets:
+    - squad
+---
+
+# bert-base-uncased-embedding-step-scheduler
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [squad](https://huggingface.co/datasets/squad) dataset.
+
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('LLukas22/bert-base-uncased-embedding-step-scheduler')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Training hyperparameters
+The following hyperparameters were used during training:
+
+- learning_rate: 2E-05
+- per device batch size: 26
+- effective batch size: 26
+- seed: 42
+- optimizer: AdamW with betas (0.9,0.999) and eps 1E-08
+- weight decay: 1E-02
+- D-Adaptation: False
+- Warmup: False
+- number of epochs: 3
+- mixed_precision_training: bf16
+
+## Training results
+| Epoch | Train Loss | Validation Loss |
+| ----- | ---------- | --------------- |
+| 0 | 0.0647 | 0.0876 |
+| 1 | 0.0328 | 0.0826 |
+| 2 | 0.0298 | 0.082 |
+
+## Evaluation results
+| Epoch | top_1 | top_3 | top_5 | top_10 | top_25 |
+| ----- | ----- | ----- | ----- | ----- | ----- |
+| 0 | 0.586 | 0.778 | 0.843 | 0.911 | 0.968 |
+| 1 | 0.596 | 0.792 | 0.853 | 0.917 | 0.969 |
+| 2 | 0.595 | 0.794 | 0.854 | 0.917 | 0.97 |
+
+## Framework versions
+- Transformers: 4.25.1
+- PyTorch: 1.13.1
+- PyTorch Lightning: 1.8.6
+- Datasets: 2.7.1
+- Tokenizers: 0.12.1
+- Sentence Transformers: 2.2.2
+
+## Additional Information
+This model was trained as part of my Master's Thesis **'Evaluation of transformer based language models for use in service information systems'**. The source code is available on [Github](https://github.com/LLukas22/Master).

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.25.1",
+    "pytorch": "1.13.1+cu117"
+  }
+}

lightning_logs/version_0/events.out.tfevents.1675779378.Lukas-Water-PC

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542acd25b484d63dbf9ea28f8b5fdae87d4082615fbb5d0e9795f8880ac454d7
+size 28587

lightning_logs/version_0/hparams.yaml

@@ -0,0 +1 @@
+{}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f991e509a39b9c56f65f267be15622df1664982d3b09f5a0ec175fe6e3ad16e
+size 437997357

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

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 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}