Upload 6 files

.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

README.md

@@ -0,0 +1,115 @@
+---
+
+language:
+
+* en
+  license: apache-2.0
+  library_name: onnxruntime
+  tags:
+* sentence-transformers
+* embeddings
+* onnx
+* int8
+* retrieval
+* semantic-search
+* rag
+* mobile
+* quantization
+  pipeline_tag: feature-extraction
+
+# MiniLM-L12 Fine-Tuned INT8 ONNX Embedding Model
+
+## Model Description
+
+This repository contains a fine-tuned **MiniLM-L12** sentence embedding model exported to **INT8 ONNX** format for efficient deployment in mobile and edge environments.
+
+The model is optimized for semantic similarity, dense retrieval, and Retrieval-Augmented Generation (RAG) applications where low latency and reduced memory usage are important.
+
+## Intended Use
+
+This model is suitable for:
+
+* Semantic search
+* Dense document retrieval
+* Retrieval-Augmented Generation (RAG)
+* FAQ matching
+* Question-answer retrieval
+* Mobile AI assistants
+* Offline embedding generation
+* Local vector search
+
+## Model Architecture
+
+* **Base Model:** `sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2`
+* **Framework:** ONNX Runtime
+* **Precision:** INT8 Quantized
+* **Embedding Type:** Dense sentence embeddings
+
+## Fine-Tuning
+
+The model was fine-tuned on a custom dataset of query–answer pairs to improve retrieval quality for local RAG scenarios.
+
+The training objective was to produce embeddings where semantically related queries and answers are positioned close together in vector space.
+
+## Evaluation Summary
+
+Performance was evaluated using retrieval metrics on a held-out test dataset.
+
+| Metric                     | Fine-Tuned Score |
+| -------------------------- | ---------------: |
+| Recall@1                   |           96.39% |
+| Recall@5                   |           99.51% |
+| Mean Reciprocal Rank (MRR) |           97.69% |
+| Accuracy                   |           96.39% |
+| F1 Score                   |           98.16% |
+
+These results indicate strong retrieval performance for semantic search and local RAG pipelines.
+
+## Files Included
+
+* `model-int8.onnx`
+* `config.json`
+* `tokenizer.json`
+* `tokenizer_config.json`
+* `special_tokens_map.json`
+
+## Usage Notes
+
+This model is intended to be executed with **ONNX Runtime**.
+
+Typical workflow:
+
+1. Tokenize the input text using the accompanying tokenizer.
+2. Run inference with the ONNX model.
+3. Apply the same pooling strategy used during training.
+4. Normalize embeddings before similarity search if required by your retrieval pipeline.
+5. Compare embeddings using cosine similarity.
+
+## Mobile Deployment
+
+The INT8 quantized model is designed for resource-constrained environments and can be integrated into:
+
+* Android applications
+* iOS applications
+* Flutter applications
+* React Native applications
+* Edge AI deployments
+
+The reduced precision helps lower memory usage and improve inference speed while maintaining strong retrieval quality.
+
+## Limitations
+
+* Retrieval quality depends on the similarity between deployment data and the fine-tuning dataset.
+* This model generates embeddings and is not intended to generate natural language responses.
+* Performance may vary across domains and languages not represented during fine-tuning.
+
+## Citation
+
+If you use this model in academic work or publications, please cite the original MiniLM architecture and the Sentence Transformers framework in addition to referencing this repository.
+
+## Acknowledgements
+
+* Sentence Transformers
+* MiniLM
+* ONNX Runtime
+* Hugging Face

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "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": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

model-int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75af5d65f259b29bb22d73616f5acc6297014b933ceea24c51a2aa87f4615f1
+size 118049319

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>"
+}