Upload L4_top student model with MTEB results

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 384,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,99 @@
+---
+language: ["ko", "en", "ja", "zh", "es", "fr", "de", "pt", "it", "ru", "ar", "hi", "th", "vi", "id", "tr", "nl", "pl"]
+tags:
+- sentence-transformers
+- intent-classification
+- multilingual
+- distillation
+- layer-pruning
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+license: apache-2.0
+---
+
+# Intent Classifier Student: L4_top
+
+Distilled multilingual sentence encoder for intent classification (Action / Recall / Other).
+
+Created by **layer pruning** from `sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2`.
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Teacher | paraphrase-multilingual-MiniLM-L12-v2 |
+| Architecture | XLM-RoBERTa (pruned) |
+| Hidden dim | 384 |
+| Layers | 4 (from 12) |
+| Layer indices | [8, 9, 10, 11] |
+| Strategy | 4 layers, top quarter (semantic-focused compact) |
+| Est. params | 103,283,328 |
+| Est. FP32 | 394.0MB |
+| Est. INT8 | 98.5MB |
+| Est. INT8 + vocab pruned | 27.1MB |
+
+## Supported Languages (18)
+
+ko, en, ja, zh, es, fr, de, pt, it, ru, ar, hi, th, vi, id, tr, nl, pl
+
+## Intended Use
+
+This is a **student encoder** designed to be used as the backbone for a lightweight
+3-class intent classifier (Action / Recall / Other) in multilingual dialogue systems.
+
+- **Action**: User requests an action (book, order, change settings, etc.)
+- **Recall**: User asks about past events or stored information
+- **Other**: Greetings, chitchat, emotions, etc.
+
+## Usage
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("L4_top")
+embeddings = model.encode(["예약 좀 해줘", "지난번 주문 뭐였지?", "안녕하세요"])
+print(embeddings.shape)  # (3, 384)
+```
+
+## MTEB Results
+
+### MassiveIntentClassification
+
+**Average: 45.26%**
+
+| Language | Score |
+|----------|-------|
+| ar | 34.77% |
+| en | 55.68% |
+| es | 42.64% |
+| ko | 47.96% |
+
+### MassiveScenarioClassification
+
+**Average: 48.79%**
+
+| Language | Score |
+|----------|-------|
+| ar | 36.89% |
+| en | 61.66% |
+| es | 47.3% |
+| ko | 49.3% |
+
+
+
+## Training / Distillation
+
+This model was created via **layer pruning** (no additional training):
+1. Load teacher: `paraphrase-multilingual-MiniLM-L12-v2` (12 layers, 384 hidden)
+2. Select layers: `[8, 9, 10, 11]`
+3. Copy embedding weights + selected layer weights
+4. Wrap with mean pooling for sentence embeddings
+
+For deployment, vocabulary pruning (250K → ~55K tokens) and INT8 quantization
+are applied to meet the ≤50MB size constraint.
+
+## Limitations
+
+- Layer pruning without fine-tuning may lose some quality vs. proper knowledge distillation
+- Vocabulary pruning limits the model to the target 18 languages
+- Designed for short dialogue utterances, not long documents

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "4.56.2",
+    "pytorch": "2.10.0+cpu"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db50f33f2f9d722559f7678622d327bebbb601a5837dc2de426ebe379778f5a0
+size 413840112

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 128,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}