Trimmed BAAI/bge-m3 for Javanese (32768 tokens)

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,69 @@
+---
+pipeline_tag: sentence-similarity
+language: jav
+license: mit
+tags:
+  - trimmed
+library_name: sentence-transformers
+base_model: BAAI/bge-m3
+base_model_relation: quantized
+datasets:
+  - Lumberjackk/fineweb-2-trimming
+---
+
+# bge-m3-jav-32768
+
+This model is a **39.18% smaller** version of [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) optimized for Javanese language via vocabulary size reduction using the [trimming](https://huggingface.co/blog/introduction-to-trimming) method.  
+
+This trimmed model should perform similarly to the original model with only **32,768 tokens** and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in Javanese were removed from the vocabulary.
+
+## Model Statistics
+
+| Metric | Original | Trimmed | Reduction |
+|--------|----------|---------|-----------|
+| **Vocabulary size** | 250,002 tokens | 32,768 tokens | **86.89%** |
+| **Model size** | 567,754,752 params | 345,307,136 params | **39.18%** |
+
+
+## Mining Dataset Statistics
+
+- **Number of texts used for mining**: 200,000 texts  
+- **Dataset**: [Lumberjackk/fineweb-2-trimming](https://huggingface.co/datasets/Lumberjackk/fineweb-2-trimming)
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/613b0a62a14099d5afed7830/7UlOxvIMVUm--Wexm9yyz.png)
+
+## Usage
+
+```python
+from sentence_transformers import SentenceTransformer
+# Download from the 🤗 Hub
+model = SentenceTransformer("lbourdois/bge-m3-jav-32768")
+# Run inference with queries and documents
+query = "My query"
+documents = [
+    "Chunk 1",
+    "Chunk 2",
+    "Chunk 3",
+]
+query_embeddings = model.encode_query(query)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# Compute similarities to determine a ranking
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+```
+
+## Citation
+
+#### BGE M3-Embedding
+
+```bibtex
+@misc{bge-m3,
+      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
+      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
+      year={2024},
+      eprint={2402.03216},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "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": 8194,
+  "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": 32768,
+  "torch_dtype": "float32"
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.33.0",
+    "pytorch": "2.1.2+cu121"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006ffe3f8ffa316758ca34dc7036bd4232f87e48004aa28626ca93f6dbd10965
+size 1381273408

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<mask>"
+  ],
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}