Add new MultiVectorEncoder model

1_Dense/config.json

@@ -0,0 +1,9 @@
+{
+    "in_features": 768,
+    "out_features": 1536,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity",
+    "module_input_name": "token_embeddings",
+    "module_output_name": "token_embeddings",
+    "use_residual": true
+}

1_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b21a25c38a742e510e671d0f07b30113bc073ea1564a9dd26bb71ebeaf19b31
+size 9437360

2_Dense/config.json

@@ -0,0 +1,9 @@
+{
+    "in_features": 1536,
+    "out_features": 768,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity",
+    "module_input_name": "token_embeddings",
+    "module_output_name": "token_embeddings",
+    "use_residual": true
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875c0da032e30d06b6c14578c3f64c6da2f4c7b0860ba6a677cc04156ca0c5eb
+size 9437360

3_Dense/config.json

@@ -0,0 +1,8 @@
+{
+    "in_features": 768,
+    "out_features": 128,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity",
+    "module_input_name": "token_embeddings",
+    "module_output_name": "token_embeddings"
+}

3_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387b61622add5ab3bedc80b057aa0444b9899269696e17181a7dbd7800d41bc4
+size 393304

4_MultiVectorMask/config.json

@@ -0,0 +1,40 @@
+{
+    "skiplist_words": [
+        "!",
+        "\"",
+        "#",
+        "$",
+        "%",
+        "&",
+        "'",
+        "(",
+        ")",
+        "*",
+        "+",
+        ",",
+        "-",
+        ".",
+        "/",
+        ":",
+        ";",
+        "<",
+        "=",
+        ">",
+        "?",
+        "@",
+        "[",
+        "\\",
+        "]",
+        "^",
+        "_",
+        "`",
+        "{",
+        "|",
+        "}",
+        "~"
+    ],
+    "skiplist_tasks": [
+        "document"
+    ],
+    "keep_only_token_ids": null
+}

5_Normalize/config.json

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

README.md

@@ -0,0 +1,210 @@
+---
+tags:
+- sentence-transformers
+- multi-vector
+- colbert
+- late-interaction
+pipeline_tag: feature-extraction
+library_name: sentence-transformers
+language: en
+license: apache-2.0
+base_model:
+- chungimungi/GLInt
+- lightonai/LateOn-regularized
+base_model_relation: merge
+---
+
+# ModernBERT-base-en-v1
+
+This is a [Multi-Vector Encoder](https://www.sbert.net/docs/multi_vector_encoder/usage/usage.html) model created by a 50/50 linear merge of [chungimungi/GLInt](https://huggingface.co/chungimungi/GLInt) and [lightonai/LateOn-regularized](https://huggingface.co/lightonai/LateOn-regularized), using the [`MultiVectorEncoder.merge`](https://www.sbert.net/docs/package_reference/multi_vector_encoder/model.html#sentence_transformers.multi_vector_encoder.model.MultiVectorEncoder.merge) method from the [sentence-transformers](https://www.SBERT.net) library. It maps inputs to sequences of 128-dimensional token-level vectors and scores them with late interaction (MaxSim), useful for semantic search with late interaction.
+
+The merged model scores above the average of its two parents on **9 of the 13 NanoBEIR datasets**, including **5 where it beats both**. It achieves a mean nDCG@10 of **0.7061**, compared with **0.6996** for GLInt and **0.6979** for LateOn-regularized, using the same inference settings for all three models.
+
+It took a whopping 6 lines of code to merge the models and set the document length, and it took about 12 seconds to execute. See [Model Creation](#model-creation) for the full generation script.
+
+## Model Details
+
+### Model Description
+
+- **Model Type:** Multi-Vector Encoder
+- **Base models:** [GLInt](https://huggingface.co/chungimungi/GLInt) and [LateOn-regularized](https://huggingface.co/lightonai/LateOn-regularized)
+- **Maximum Sequence Length:** 8192 tokens
+    - **Maximum Query Length:** 32 tokens
+    - **Maximum Document Length:** 8192 tokens
+- **Output Dimensionality:** 128 dimensions
+- **Similarity Function:** MaxSim
+- **Supported Modality:** Text
+- **Language:** English
+- **License:** Apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Documentation:** [Multi-Vector Encoder Documentation](https://www.sbert.net/docs/multi_vector_encoder/usage/usage.html)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
+- **Hugging Face:** [Multi-Vector Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=multi-vector)
+
+### Full Model Architecture
+
+```
+MultiVectorEncoder(
+  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'query_length': 32, 'document_length': 8192, 'architecture': 'ModernBertModel'})
+  (1): Dense({'in_features': 768, 'out_features': 1536, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings', 'use_residual': True})
+  (2): Dense({'in_features': 1536, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings', 'use_residual': True})
+  (3): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
+  (4): MultiVectorMask({'skiplist_words': ['!', '"', '#', '$', '%', '&', "'", '(', ')', '*', '+', ',', '-', '.', '/', ':', ';', '<', '=', '>', '?', '@', '[', '\\', ']', '^', '_', '`', '{', '|', '}', '~'], 'skiplist_tasks': ['document'], 'keep_only_token_ids': None})
+  (5): Normalize({'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
+)
+```
+
+## 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 MultiVectorEncoder
+
+model = MultiVectorEncoder("multi-vector-encoder/ModernBERT-base-en-v1")
+queries = [
+    'Which planet is known as the Red Planet?',
+]
+documents = [
+    "Venus is often called Earth's twin because of its similar size and proximity.",
+    'Mars, known for its reddish appearance, is often referred to as the Red Planet.',
+    'Saturn, famous for its rings, is sometimes mistaken for the Red Planet.',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings[0].shape, document_embeddings[0].shape)
+# (12, 128) (18, 128)
+
+# Get the MaxSim similarity scores
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[11.4814, 11.6525, 11.6232]])
+```
+
+## Evaluation
+
+### Metrics
+
+#### NanoBEIR
+
+* Dataset: [NanoBEIR-en](https://huggingface.co/datasets/sentence-transformers/NanoBEIR-en)
+* Evaluated with `MultiVectorNanoBEIREvaluator` on all 13 datasets.
+* Query length: 32 tokens. Document length: 8192 tokens (expanded from 300 for GLInt and LateOn-regularized).
+* Metric: nDCG@10. The mean is unweighted across datasets.
+
+The parent models were evaluated with the same prompts and length limits.
+
+| Dataset | ModernBERT-base-en-v1 | GLInt | LateOn-regularized |
+| --- | --- | --- | --- |
+| msmarco | <u>0.736155</u> | 0.728477 | 0.707793 |
+| nq | <u>0.818848</u> | 0.818032 | 0.782732 |
+| fiqa2018 | <u>0.640317</u> | 0.625973 | 0.625546 |
+| nfcorpus | 0.393756 | <u>0.399912</u> | 0.391630 |
+| scidocs | 0.435285 | 0.435472 | <u>0.444901</u> |
+| arguana | <u>0.588440</u> | 0.569680 | 0.561172 |
+| dbpedia | 0.703868 | <u>0.709176</u> | 0.678083 |
+| quoraretrieval | <u>0.990127</u> | 0.983948 | 0.986797 |
+| touche2020 | 0.692082 | <u>0.696390</u> | 0.686696 |
+| climatefever | 0.484580 | 0.418405 | <u>0.521409</u> |
+| fever | 0.966278 | <u>0.969763</u> | 0.966278 |
+| hotpotqa | 0.930661 | <u>0.934504</u> | 0.917731 |
+| scifact | 0.799062 | <u>0.804524</u> | 0.802028 |
+| **mean** | **<u>0.706112</u>** | **0.699558** | **0.697907** |
+
+## Model Creation
+
+The backbone and all three projection layers were merged in fp32 with equal weights from [GLInt](https://huggingface.co/chungimungi/GLInt) and [LateOn-regularized](https://huggingface.co/lightonai/LateOn-regularized), without any training.
+
+This is all it took:
+
+```python
+# pip install "sentence-transformers[merge]"
+from sentence_transformers import MultiVectorEncoder
+
+# Load the GLInt and LateOn-regularized models,
+# matching the latter's special token config
+glint = MultiVectorEncoder(
+    "chungimungi/GLInt",
+    config_kwargs={
+        "bos_token_id": 50281,
+        "eos_token_id": 50282,
+        "pad_token_id": 50283,
+    },
+    processor_kwargs={"model_max_length": 8192, "max_length": 8192},
+)
+lateon = MultiVectorEncoder("lightonai/LateOn-regularized")
+
+# Merge using simple 50/50 linear
+model = MultiVectorEncoder.merge(
+    [glint, lateon],
+    method="linear",
+    parameters={"weight": [0.5, 0.5]},
+)
+# Increase the document length from 300 to 8192 tokens
+model[0].document_length = 8192
+# And save it for reuse
+model.save_pretrained("ModernBERT-base-en-v1")
+```
+
+### Framework Versions
+
+- Python: 3.12.3
+- Sentence Transformers: 6.2.0
+- Transformers: 5.4.0
+- PyTorch: 2.11.0+cu128
+- Accelerate: 1.13.0
+- Datasets: 4.8.5
+- Tokenizers: 0.22.2
+
+## Citation
+
+### BibTeX
+
+#### LateOn Regularization
+
+```bibtex
+@misc{chaffin2026lateonregularization,
+  title={Party is over: regularizing ColBERT models to fix efficient ANN methods},
+  author={Chaffin, Antoine},
+  year={2026},
+  howpublished={\url{https://huggingface.co/blog/lightonai/lateon-regularization}},
+}
+```
+
+#### GLInt
+
+```bibtex
+@misc{aarush2026glint,
+  title={GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval},
+  author={Aarush},
+  year={2026},
+  howpublished={\url{https://huggingface.co/blog/chungimungi/glint}},
+}
+```
+
+### Mergekit
+
+```bibtex
+@inproceedings{goddard-etal-2024-arcees,
+    title = "Arcee{'}s {M}erge{K}it: A Toolkit for Merging Large Language Models",
+    author = "Goddard, Charles and Siriwardhana, Shamane and Ehghaghi, Malikeh and Meyers, Luke and Karpukhin, Vladimir and Benedict, Brian and McQuade, Mark and Solawetz, Jacob",
+    editor = "Dernoncourt, Franck and Preo{\c{t}}iuc-Pietro, Daniel and Shimorina, Anastasia",
+    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
+    month = nov,
+    year = "2024",
+    address = "Miami, Florida, US",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2024.emnlp-industry.36",
+    doi = "10.18653/v1/2024.emnlp-industry.36",
+    pages = "477--485",
+}
+```

config.json

@@ -0,0 +1,78 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "local_attention": 128,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 160000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.21.0.dev0",
+  "vocab_size": 50370
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.10.0+cu128",
+    "sentence_transformers": "6.3.0.dev0",
+    "transformers": "5.21.0.dev0"
+  },
+  "default_prompt_name": null,
+  "model_type": "MultiVectorEncoder",
+  "prompts": {
+    "document": "[D] ",
+    "query": "[Q] "
+  },
+  "similarity_fn_name": "maxsim"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f0ac605ba5687101f96281169c8b4f963a73d4f7aac2b8225de2040c3fb17d0
+size 596076280

modules.json

@@ -0,0 +1,38 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Dense",
+    "type": "sentence_transformers.base.modules.dense.Dense"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.base.modules.dense.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Dense",
+    "type": "sentence_transformers.base.modules.dense.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4",
+    "path": "4_MultiVectorMask",
+    "type": "sentence_transformers.multi_vector_encoder.modules.multi_vector_mask.MultiVectorMask"
+  },
+  {
+    "idx": 5,
+    "name": "5",
+    "path": "5_Normalize",
+    "type": "sentence_transformers.base.modules.normalize.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,12 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings",
+    "query_length": 32,
+    "document_length": 8192
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 8192,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "[MASK]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}