Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 1024,
+  "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
+}

README.md

@@ -1,3 +1,95 @@
----
-license: mit
----
+---
+base_model: intfloat/multilingual-e5-large-instruct
+base_model_relation: quantized
+library_name: transformers.js
+pipeline_tag: feature-extraction
+tags:
+  - transformers.js
+  - sentence-transformers
+  - onnx
+  - feature-extraction
+  - sentence-similarity
+  - mteb
+  - xlm-roberta
+  - e5
+  - multilingual
+language:
+  - multilingual
+license: mit
+---
+
+# multilingual-e5-large-instruct (ONNX)
+
+ONNX export of [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct)
+with fp16 and int8 quantized variants.
+
+Compatible with both [`@huggingface/transformers`](https://huggingface.co/docs/transformers.js) (JavaScript) and
+[`sentence-transformers`](https://www.sbert.net/) (Python).
+
+## Available Models
+
+| File | Format | Size | Description |
+|------|--------|------|-------------|
+| `onnx/model.onnx` + `model.onnx_data` | fp32 | 2.1 GB | Full precision, external data format |
+| `onnx/model_fp16.onnx` | fp16 | 1.0 GB | Half precision, negligible quality loss |
+| `onnx/model_quantized.onnx` | int8 | 535 MB | Dynamic quantization, smallest size |
+
+## Usage with Transformers.js
+
+```javascript
+import { pipeline } from "@huggingface/transformers";
+
+const extractor = await pipeline(
+  "feature-extraction",
+  "lmo3/multilingual-e5-large-instruct",
+  { dtype: "fp16" } // or "q8" for int8, omit for fp32
+);
+
+// Queries use the instruct format
+const query = "Instruct: Retrieve semantically similar text.\nQuery: How is the weather today?";
+const queryEmbedding = await extractor(query, { pooling: "mean", normalize: true });
+
+// Documents are embedded as-is (no prefix)
+const docEmbedding = await extractor("It is sunny outside", { pooling: "mean", normalize: true });
+```
+
+## Usage with sentence-transformers (Python)
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("lmo3/multilingual-e5-large-instruct")
+
+# Queries use the instruct format
+queries = ["Instruct: Retrieve semantically similar text.\nQuery: How is the weather today?"]
+docs = ["It is sunny outside"]
+
+query_embeddings = model.encode(queries)
+doc_embeddings = model.encode(docs)
+```
+
+## Key Differences from Base E5
+
+This is the **instruct** variant of multilingual-e5-large. The key difference:
+
+- **Queries** must be prefixed with `Instruct: <task description>\nQuery: `
+- **Documents** are embedded as-is, with no prefix
+
+The instruction tells the model what retrieval task you're performing, improving embedding quality.
+See the [original model card](https://huggingface.co/intfloat/multilingual-e5-large-instruct) for task-specific instructions and benchmark results.
+
+## Export Details
+
+- Exported via [Optimum](https://huggingface.co/docs/optimum) with ONNX opset 18
+- fp16 quantized via `onnxruntime.transformers.optimizer`
+- int8 quantized via `onnxruntime.quantization.quantize_dynamic`
+- `config.json` patched with `transformers.js_config` for automatic external data handling
+
+## Original Model
+
+This is a conversion of [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct):
+
+- **Architecture**: XLM-RoBERTa Large (24 layers, 1024 hidden, 16 heads)
+- **Embedding dimension**: 1024
+- **Languages**: 100+ languages
+- **License**: MIT

config.json

@@ -0,0 +1,32 @@
+{
+  "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,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": true
+    }
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.4.0.dev0",
+    "transformers": "4.37.0",
+    "pytorch": "2.1.0+cu121"
+  }
+}

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"
+  }
+]

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd3abcc64fd6c7ded4447b51b7b63af2c6db07d349d77712431d955d4094c50
+size 433455

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c13ca44e40a7ee86b461398cdee003d656e39f3fa87e1b3152fbada3e61b506
+size 2235367440

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2873639541febeccc6d1b899da65ec6ac6756f5f3f2b4f51a3ad674b537fbaf
+size 1117761596

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced1bc687c0058326fea2b79c635cf451b4c0f963f98dc54277f003f3b6d921c
+size 560553629

sentence_xlm-roberta_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}