Release v1

.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 +1,5 @@
+{
+    "embedding_dimension": 768,
+    "pooling_mode": "mean",
+    "include_prompt": true
+}

2_Normalize/config.json

@@ -0,0 +1,4 @@
+{
+    "module_input_name": "sentence_embedding",
+    "module_output_name": "sentence_embedding"
+}

README.md

@@ -1,3 +1,32 @@
 ---
 license: apache-2.0
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+base_model: unsloth/embeddinggemma-2
+tags:
+- sentence-transformers
+- feature-extraction
 ---
+
+# MoMa analytical pattern embedder
+
+EmbeddingGemma 2 fine-tuned to match a user's task to the Analytical Pattern (AP) that
+answers it, for the search of the DataGEMS MoMa Management service. Text only, 768
+dimensions.
+
+It is a LoRA adapter merged into `unsloth/embeddinggemma-2` at revision `c8f89cc7ecb4ba5122cd15fdd487422b2b487daf`.
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("<this repository>", config_kwargs={"vision_config": None, "audio_config": None})
+task = model.encode_query("Which students are at risk of failing?")
+aps = model.encode_document(["Translates a natural-language string into a safe SQL query, ..."])
+```
+
+Queries and AP texts are given different prefixes, so use `encode_query` and
+`encode_document` rather than `encode`. The AP text the model was trained on is the one
+`AnalyticalPattern.describe()` builds from an AP's operators, not the AP's own description.
+
+Dataset, training and benchmark:
+https://github.com/datagems-eosc/moma-management/tree/main/packages/analytical-pattern-embedder

chat_template.jinja

@@ -0,0 +1 @@
+{%- for msg in messages if msg.get('role') == 'system' -%}{%- if msg.get('content') is string -%}{{ msg['content'] }}{%- else -%}{%- for item in msg['content'] if item.get('type') == 'text' -%}{{ item['text'] }}{%- endfor -%}{%- endif -%}{%- endfor -%}{%- for msg in messages if msg.get('role') != 'system' -%}{%- if msg.get('content') is string -%}{{ msg['content'] }}{%- else -%}{%- set existing_text = msg['content'] | selectattr('type', 'equalto', 'text') | map(attribute='text') | join -%}{%- set has_manual_placeholders = ('<|image|>' in existing_text) or ('<|video|>' in existing_text) or ('<|audio|>' in existing_text) -%}{%- for item in msg['content'] -%}{%- if item.get('type') == 'text' -%}{{ item['text'] }}{%- elif not has_manual_placeholders and item.get('type') == 'image' -%}<|image|>{%- elif not has_manual_placeholders and item.get('type') == 'video' -%}<|video|>{%- elif not has_manual_placeholders and item.get('type') == 'audio' -%}<|audio|>{%- endif -%}{%- endfor -%}{%- endif -%}{%- endfor -%}

config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "EmbeddingGemma2Model"
+  ],
+  "audio_config": null,
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "embedding_gemma2",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "embedding_dim": 768,
+    "eos_token_id": 1,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 512,
+    "hidden_size_per_layer_input": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "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": 262144,
+    "model_type": "embedding_gemma2_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "pad_token_id": 0,
+    "per_layer_config": {
+      "05": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "11": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "17": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "23": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      }
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "vocab_size": 262144
+  },
+  "transformers_version": "5.19.0",
+  "video_token_id": 258884,
+  "vision_config": null,
+  "vision_soft_tokens_per_image": 280
+}

config_sentence_transformers.json

@@ -0,0 +1,32 @@
+{
+  "__version__": {
+    "pytorch": "2.14.1+cpu",
+    "sentence_transformers": "6.1.0",
+    "transformers": "5.19.0"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "BitextMining": "task: search result | query: ",
+    "Classification": "task: classification | query: ",
+    "Clustering": "task: clustering | query: ",
+    "CodeRetrieval": "task: code retrieval | query: ",
+    "Document": "title: none | text: ",
+    "FactChecking": "task: fact checking | query: ",
+    "InstructionRetrieval": "task: code retrieval | query: ",
+    "MultilabelClassification": "task: classification | query: ",
+    "PairClassification": "task: sentence similarity | query: ",
+    "QuestionAnswering": "task: question answering | query: ",
+    "Reranking": "task: search result | query: ",
+    "Retrieval": "task: search result | query: ",
+    "Retrieval-document": "title: none | text: ",
+    "Retrieval-query": "task: search result | query: ",
+    "STS": "task: sentence similarity | query: ",
+    "SearchQuery": "task: search result | query: ",
+    "SentenceSimilarity": "task: sentence similarity | query: ",
+    "Summarization": "task: sentence similarity | query: ",
+    "document": "title: none | text: ",
+    "query": "task: search result | query: "
+  },
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24239438ea15a2c71f361765bde3f95b4c3f991c77bb2b1c3aa44f2ee05bb09
+size 542056448

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.base.modules.normalize.Normalize"
+  }
+]

processor_config.json

@@ -0,0 +1,78 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 280,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "EmbeddingGemma2Processor",
+  "video_processor": {
+    "add_timestamps": false,
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 1,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_frames": 32,
+    "max_soft_tokens": 140,
+    "overflow_strategy": "uniform",
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "EmbeddingGemma2VideoProcessor"
+  }
+}

sentence_bert_config.json

@@ -0,0 +1,27 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "image": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "audio": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "video": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "message": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state",
+            "format": "structured"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8228146e873f0cf434e8ce247e13698a54e909a0de0eb46010aac6d7119d6029
+size 32170763

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>",
+    "video_token": "<|video|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "EmbeddingGemma2Processor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "video_token": "<|video|>"
+}