Add new SentenceTransformer model.

1_Pooling/config.json

@@ -1,10 +1,10 @@
 {
-  "word_embedding_dimension": 768,
-  "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,
-  "include_prompt": true
+    "word_embedding_dimension": 768,
+    "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,
+    "include_prompt": true
 }

README.md

@@ -1,95 +1,144 @@
 ---
-library_name: sentence-transformers
-pipeline_tag: sentence-similarity
 tags:
 - sentence-transformers
-- feature-extraction
 - sentence-similarity
-- transformers
-
+- feature-extraction
+- dense
+base_model: google/embeddinggemma-300m
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
 ---
 
-# Randstad/gemma-embedding-st
+# SentenceTransformer based on google/embeddinggemma-300m
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
-<!--- Describe your model here -->
+## Model Details
 
-## Usage (Sentence-Transformers)
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
 
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
 
 ```
-pip install -U sentence-transformers
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
+  (1): Pooling({'word_embedding_dimension': 768, '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, 'include_prompt': True})
+)
 ```
 
-Then you can use the model like this:
+## Usage
 
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('Randstad/gemma-embedding-st')
+# Download from the 🤗 Hub
+model = SentenceTransformer("Randstad/gemma-embedding-st")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
 embeddings = model.encode(sentences)
-print(embeddings)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.9254, 0.9106],
+#         [0.9254, 1.0000, 0.9032],
+#         [0.9106, 0.9032, 1.0000]])
 ```
 
+<!--
+### Direct Usage (Transformers)
 
+<details><summary>Click to see the direct usage in Transformers</summary>
 
-## Usage (HuggingFace Transformers)
-Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+</details>
+-->
 
-```python
-from transformers import AutoTokenizer, AutoModel
-import torch
+<!--
+### Downstream Usage (Sentence Transformers)
 
+You can finetune this model on your own dataset.
 
-#Mean Pooling - Take attention mask into account for correct averaging
-def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
-    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+<details><summary>Click to expand</summary>
 
+</details>
+-->
 
-# Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+<!--
+### Out-of-Scope Use
 
-# Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('Randstad/gemma-embedding-st')
-model = AutoModel.from_pretrained('Randstad/gemma-embedding-st')
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
 
-# Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+<!--
+## Bias, Risks and Limitations
 
-# Compute token embeddings
-with torch.no_grad():
-    model_output = model(**encoded_input)
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
 
-# Perform pooling. In this case, mean pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+<!--
+### Recommendations
 
-print("Sentence embeddings:")
-print(sentence_embeddings)
-```
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
 
+## Training Details
 
+### Framework Versions
+- Python: 3.10.18
+- Sentence Transformers: 5.1.1
+- Transformers: 4.52.4
+- PyTorch: 2.7.1+cu126
+- Accelerate: 1.8.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
 
-## Evaluation Results
+## Citation
 
-<!--- Describe how your model was evaluated -->
+### BibTeX
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=Randstad/gemma-embedding-st)
+<!--
+## Glossary
 
+*Clearly define terms in order to be accessible across audiences.*
+-->
 
+<!--
+## Model Card Authors
 
-## Full Model Architecture
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: Gemma3TextModel 
-  (1): Pooling({'word_embedding_dimension': 768, '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, 'include_prompt': True})
-)
-```
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
 
-## Citing & Authors
+<!--
+## Model Card Contact
 
-<!--- Describe where people can find more information -->
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -7,6 +7,7 @@
   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
+  "cache_implementation": "hybrid",
   "dtype": "float32",
   "eos_token_id": 1,
   "final_logit_softcapping": null,
@@ -52,8 +53,10 @@
   "rope_local_base_freq": 10000.0,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
-  "sliding_window": 257,
-  "transformers_version": "4.57.1",
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
   "use_bidirectional_attention": true,
   "use_cache": true,
   "vocab_size": 262144

config_sentence_transformers.json

@@ -1,9 +1,14 @@
 {
+  "model_type": "SentenceTransformer",
   "__version__": {
-    "sentence_transformers": "2.7.0",
-    "transformers": "4.57.1",
-    "pytorch": "2.3.1+cu121"
+    "sentence_transformers": "5.1.1",
+    "transformers": "4.52.4",
+    "pytorch": "2.7.1+cu126"
   },
-  "prompts": {},
-  "default_prompt_name": null
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
 }

sentence_bert_config.json

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6852f8d561078cc0cebe70ca03c5bfdd0d60a45f9d2e0e1e4cc05b68e9ec329e
-size 33385008
+oid sha256:c79a190be01275b078b3574d02188abc5784e5651a101b20d826371ba8e897dc
+size 33385261

tokenizer_config.json

@@ -51334,7 +51334,7 @@
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "model_max_length": 2048,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "padding_side": "right",
   "sp_model_kwargs": null,