初始化项目，由ModelHub XC社区提供模型

Model: Adc05102002/bge-m3-vi-base
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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

README.md

@@ -0,0 +1,61 @@
+---
+language:
+- multilingual
+license: mit
+library_name: transformers
+pipeline_tag: sentence-similarity
+tags:
+- embeddings
+- text-embeddings-inference
+- bge
+- bge-m3
+- multilingual
+- retrieval
+- semantic-search
+- xlm-roberta
+- custom-tokenizer
+- long-context
+base_model: BAAI/bge-m3
+model_type: xlm-roberta
+---
+
+# BGE-M3 Custom Tokenizer (8.5K Vocab)
+
+A customized version of :contentReference[oaicite:0]{index=0} with a newly trained tokenizer optimized for domain-specific multilingual retrieval workloads.
+
+This model replaces the original XLM-R tokenizer vocabulary with a compact 8.5K-token tokenizer trained on a custom corpus.
+
+## Highlights
+
+- Based on `BAAI/bge-m3`
+- Custom tokenizer trained from scratch
+- Reduced vocabulary size: **8500**
+- Long-context support: **8192 tokens**
+- Multilingual retrieval and embedding model
+- Optimized for:
+  - semantic search
+  - RAG pipelines
+  - dense retrieval
+  - domain-specific embeddings
+
+---
+
+# Model Details
+
+## Base Model
+
+- Architecture: XLM-RoBERTa
+- Original model: `BAAI/bge-m3`
+- Embedding dimension: 1024
+- Transformer encoder model
+
+## Tokenizer
+
+The original tokenizer was replaced with a newly trained tokenizer using:
+
+```python
+tokenizer = base_tokenizer.train_new_from_iterator(
+    batch_iterator(),
+    vocab_size=8500,
+    min_frequency=2,
+)

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4026,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 6592
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca6d364b994d2fbb3babe7de36fad00eb8f69ad12fc4bf91cd45856cdd08666
+size 1256984264

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}