Upload fine-tuned EmbeddingGemma ONNX for web deployment

.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 +1,98 @@
+---
+library_name: transformers.js
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- transformers.js
+- onnx
+- biblical-search
+- semantic-search
+- embeddinggemma
+- fine-tuned
+license: apache-2.0
+datasets:
+- biblical-text-pairs
+metrics:
+- accuracy@1: 12.00%
+- accuracy@3: 15.00%  
+- accuracy@10: 31.00%
+language:
+- en
+---
+
+# EmbeddingGemma-300M Fine-tuned for Biblical Text Search (ONNX)
+
+This is the ONNX version of our fine-tuned EmbeddingGemma-300M model specialized for biblical text search and retrieval. This version is optimized for web deployment using transformers.js.
+
+## Model Performance
+
+- **Accuracy@1**: 12.00% (13x improvement over base model)
+- **Accuracy@3**: 15.00%
+- **Accuracy@10**: 31.00%
+- **Training Steps**: 25 (optimal stopping point)
+- **Base Model Accuracy@1**: 0.91%
+
+## Usage with Transformers.js
+
+```javascript
+import { AutoTokenizer, AutoModel } from '@huggingface/transformers';
+
+// Load the model
+const model = await AutoModel.from_pretrained('dpshade22/embeddinggemma-scripture-v1-onnx');
+const tokenizer = await AutoTokenizer.from_pretrained('dpshade22/embeddinggemma-scripture-v1-onnx');
+
+// Encode queries (use search_query: prefix)
+const query = "search_query: What is love?";
+const query_embedding = await model.encode([query]);
+
+// Encode documents (use search_document: prefix)  
+const document = "search_document: Love is patient and kind";
+const doc_embedding = await model.encode([document]);
+```
+
+## Prefixes
+
+For optimal performance, use these prefixes:
+
+- **Queries**: `"search_query: your question here"`
+- **Documents**: `"search_document: scripture text here"`
+
+## Model Details
+
+- **Base Model**: `google/embeddinggemma-300m`
+- **Training Data**: 26,276 biblical text pairs
+- **Training Steps**: 25 steps (optimal stopping point)
+- **Learning Rate**: 2.0e-04
+- **Batch Size**: 8
+- **Output Dimensions**: 768D (supports Matryoshka 384D, 128D)
+- **ONNX Conversion**: Using nixiesearch/onnx-convert specialized tool
+
+## Training Details
+
+- **Training Data**: 26,276 biblical text pairs
+- **Learning Rate**: 2.0e-04
+- **Batch Size**: 8
+- **Training Strategy**: Early stopping at 25 steps to prevent overfitting
+- **Output Dimensions**: 768D (supports Matryoshka 384D, 128D)
+
+## Intended Use
+
+This model is designed for:
+- Biblical text search and retrieval in web applications
+- Finding relevant scripture passages
+- Semantic similarity of religious texts
+- Question answering on biblical topics
+- Offline PWA applications using transformers.js
+
+## Conversion Details
+
+- **Converted using**: nixiesearch/onnx-convert specialized tool
+- **ONNX Opset**: 17
+- **Optimization Level**: 1
+- **Max difference from original**: 1.9e-05 (within acceptable tolerance)
+
+## Related Models
+
+- **Original PyTorch version**: dpshade22/embeddinggemma-scripture-v1
+- **Base model**: google/embeddinggemma-300m
+- **Reference ONNX**: onnx-community/embeddinggemma-300m-ONNX

config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3TextModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "export_model_type": "transformer",
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 3,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_bidirectional_attention": true,
+  "use_cache": true,
+  "vocab_size": 262144
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f055dfae8de21cdf8180314311d3cba2435f38f7c2204131ef708955c3bece05
+size 1231684213

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f055dfae8de21cdf8180314311d3cba2435f38f7c2204131ef708955c3bece05
+size 1231684213

onnx/model_opt1_Float32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425f0ed772ce3861172142b543fa73fd8f26ef2185e0bcdbbac61b53a2077173
+size 1231131653

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "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:c79a190be01275b078b3574d02188abc5784e5651a101b20d826371ba8e897dc
+size 33385261