Initial upload of paraphrase-multilingual-MiniLM-L12-v2 exports

.gitattributes

@@ -33,3 +33,12 @@ 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
+xnnpack/distiluse-base-multilingual-cased-v2_xnnpack_fp32.pte filter=lfs diff=lfs merge=lfs -text
+xnnpack/distiluse-base-multilingual-cased-v2_xnnpack_8da4w.pte filter=lfs diff=lfs merge=lfs -text
+coreml/distiluse-base-multilingual-cased-v2_coreml_fp16.pte filter=lfs diff=lfs merge=lfs -text
+coreml/distiluse-base-multilingual-cased-v2_coreml_fp32.pte filter=lfs diff=lfs merge=lfs -text
+coreml/paraphrase-multilingual-MiniLM-L12-v2_coreml_fp16.pte filter=lfs diff=lfs merge=lfs -text
+coreml/paraphrase-multilingual-MiniLM-L12-v2_coreml_fp32.pte filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+xnnpack/paraphrase-multilingual-MiniLM-L12-v2_xnnpack_8da4w.pte filter=lfs diff=lfs merge=lfs -text
+xnnpack/paraphrase-multilingual-MiniLM-L12-v2_xnnpack_fp32.pte filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+---
+
+# Introduction
+
+This repository hosts the [paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/tree/main) model for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes the model exported for both the **XNNPACK** (Android / generic CPU) and **CoreML** (Apple) delegates, in multiple precisions, ready for use in the **ExecuTorch** runtime.
+
+If you'd like to run these models in your own ExecuTorch runtime, refer to the [official documentation](https://pytorch.org/executorch/stable/index.html) for setup instructions.
+
+## Compatibility
+
+If you intend to use this model outside of React Native ExecuTorch, make sure your runtime is compatible with the **ExecuTorch** version used to export the `.pte` files. For more details, see the compatibility note in the [ExecuTorch GitHub repository](https://github.com/pytorch/executorch/blob/11d1742fdeddcf05bc30a6cfac321d2a2e3b6768/runtime/COMPATIBILITY.md?plain=1#L4). If you work with React Native ExecuTorch, the constants from the library will guarantee compatibility with the runtime used behind the scenes.
+
+These models were exported using React Native ExecuTorch `v0.9.0`, which ships an ExecuTorch runtime derived from the `v1.2.0` release branch and an updated `pytorch/extension/llm/tokenizers` build that adds Unigram / Precompiled normalizer / Metaspace decoder support — required to load this model's tokenizer. **No forward compatibility** is guaranteed — older versions of the runtime may not work with these files; in particular, RNE ≤ 0.8.x cannot load `tokenizer.json` and will fail at the tokenizer-load step.
+
+## Variant Matrix
+
+| Delegate | Precision | File                                                                              | Size    | Notes                                                                                                                                                                                                                          |
+|----------|-----------|-----------------------------------------------------------------------------------|---------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| XNNPACK  | fp32      | `xnnpack/paraphrase-multilingual-MiniLM-L12-v2_xnnpack_fp32.pte`                  | 449 MB  | Baseline. Works on Android / iOS / generic CPU.                                                                                                                                                                                |
+| XNNPACK  | 8da4w     | `xnnpack/paraphrase-multilingual-MiniLM-L12-v2_xnnpack_8da4w.pte`                 | 379 MB  | Int8 dynamic activation + Int4 weight (torchao), group_size=32. Embeddings stay fp32 — the bulk of the file is the 250 037 × 384 vocab matrix (≈ 384 MB), so the linear-layer quantization yields only a modest size win.       |
+| CoreML   | fp32      | `coreml/paraphrase-multilingual-MiniLM-L12-v2_coreml_fp32.pte`                    | 449 MB  | Apple Neural Engine / GPU / CPU, float32 compute.                                                                                                                                                                              |
+| CoreML   | fp16      | `coreml/paraphrase-multilingual-MiniLM-L12-v2_coreml_fp16.pte`                    | 225 MB  | Half-sized via `compute_precision=FLOAT16` at CoreML compile. Cleanest size win on iOS.                                                                                                                                        |
+
+Pick the variant that matches your platform + size/quality trade-off. The CoreML variants only load on Apple platforms; the XNNPACK variants load everywhere.
+
+## Repository Structure
+
+- `xnnpack/` — `.pte` files partitioned for the XNNPACK delegate.
+- `coreml/` — `.pte` files partitioned for the CoreML delegate (iOS / macOS only).
+- `tokenizer.json` — HuggingFace fast-tokenizer dump (Unigram model + Precompiled normalizer + Metaspace decoder, derived from the upstream SentencePiece tokenizer). Wire this to `tokenizerSource`.
+- `config.json`, `tokenizer_config.json` — upstream model/tokenizer configs, kept for reference and for non-RNE consumers.
+
+The `.pte` path goes to `modelSource`; `tokenizer.json` is shared across all variants.
+
+## Model details
+
+- Architecture: 12-layer, 12-head BERT with hidden size 384 (initialized from `xlm-roberta-base`) + mean pooling + L2 norm. No additional dense projection head — the model output dim equals the encoder hidden size.
+- Output dimension: **384**.
+- Max sequence length: **126** tokens (128 − 2 for the `<s>` / `</s>` wrapping; the exporter concatenates these XLM-R-style start/end tokens at id 0 / 2 inside the program).
+- Vocabulary: 250 037 SentencePiece pieces.
+- Languages: 50+ (multilingual).
+- Typical strength: cross-lingual sentence similarity and medium-length sentence retrieval — designed for paraphrase mining and cross-lingual search. Short single-word queries in non-English languages are this model's weakest case; longer sentences and/or English inputs give markedly better ranking.
+
+## Export notes
+
+The exporter wraps the HuggingFace transformer with the standard sentence-transformers contract: token IDs go in, the program prepends `<s>` and appends `</s>`, mean pooling is applied to the last hidden state weighted by the attention mask, and the output is L2-normalized to a 384-d vector.
+
+Unsupported combinations (rejected by the exporter, documented for reference):
+
+- **XNNPACK + fp16** — `model.to(torch.float16)` causes softmax / LayerNorm overflow and the runtime output is NaN. XNNPACK's size wins come from quantization, not fp16.
+- **CoreML + 8da4w** — `coremltools` has no MIL mapping for the `torch.int8` tensors torchao emits (`KeyError: torch.int8`). The CoreML-native way to shrink further is `ct.optimize.coreml` palette/linear quantization, not torchao source transforms.

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

coreml/paraphrase-multilingual-MiniLM-L12-v2_coreml_fp16.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5a00d98d653bbfd34e1a1ea0fbd4b1c7efcb00e9ad6035a671c23725352fe2
+size 235546731

coreml/paraphrase-multilingual-MiniLM-L12-v2_coreml_fp32.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb02c21323510e759fd6379d903ba734b044fd8249cf601c8754a0b2b1d643af
+size 470468177

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 @@
+{"do_lower_case": true, "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer", "tokenizer_class": "PreTrainedTokenizerFast"}

xnnpack/paraphrase-multilingual-MiniLM-L12-v2_xnnpack_8da4w.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5cbf80384160988c10e117575eb479b56cdc78eb3ee0cff40c02d00eb2a92c
+size 397309568

xnnpack/paraphrase-multilingual-MiniLM-L12-v2_xnnpack_fp32.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a53d2693f881857866eef57656224cc63f6668459bb32e21858e15a9e13c4b2
+size 470274304