Upload 13 files

Configured German model added

.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_Dense/config.json

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

1_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082cc1e4b9bf47d7eb8979a9e2cc643f3c3ea07dc68a706c58823316235025e1
+size 393304

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "antoinelouis/colbert-xm",
+  "adapter_layer_norm": false,
+  "adapter_reduction_factor": 2,
+  "adapter_reuse_layer_norm": true,
+  "architectures": [
+    "XmodModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "default_language": "de_DE",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "languages": [
+    "en_XX",
+    "id_ID",
+    "vi_VN",
+    "ru_RU",
+    "fa_IR",
+    "sv_SE",
+    "ja_XX",
+    "fr_XX",
+    "de_DE",
+    "ro_RO",
+    "ko_KR",
+    "hu_HU",
+    "es_XX",
+    "fi_FI",
+    "uk_UA",
+    "da_DK",
+    "pt_XX",
+    "no_XX",
+    "th_TH",
+    "pl_PL",
+    "bg_BG",
+    "nl_XX",
+    "zh_CN",
+    "he_IL",
+    "el_GR",
+    "it_IT",
+    "sk_SK",
+    "hr_HR",
+    "tr_TR",
+    "ar_AR",
+    "cs_CZ",
+    "lt_LT",
+    "hi_IN",
+    "zh_TW",
+    "ca_ES",
+    "ms_MY",
+    "sl_SI",
+    "lv_LV",
+    "ta_IN",
+    "bn_IN",
+    "et_EE",
+    "az_AZ",
+    "sq_AL",
+    "sr_RS",
+    "kk_KZ",
+    "ka_GE",
+    "tl_XX",
+    "ur_PK",
+    "is_IS",
+    "hy_AM",
+    "ml_IN",
+    "mk_MK",
+    "be_BY",
+    "la_VA",
+    "te_IN",
+    "eu_ES",
+    "gl_ES",
+    "mn_MN",
+    "kn_IN",
+    "ne_NP",
+    "sw_KE",
+    "si_LK",
+    "mr_IN",
+    "af_ZA",
+    "gu_IN",
+    "cy_GB",
+    "eo_EO",
+    "km_KH",
+    "ky_KG",
+    "uz_UZ",
+    "ps_AF",
+    "pa_IN",
+    "ga_IE",
+    "ha_NG",
+    "am_ET",
+    "lo_LA",
+    "ku_TR",
+    "so_SO",
+    "my_MM",
+    "or_IN",
+    "sa_IN"
+  ],
+  "layer_norm_eps": 1e-05,
+  "ln_before_adapter": true,
+  "max_position_embeddings": 514,
+  "model_type": "xmod",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "pre_norm": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250004
+}

config_sentence_transformers.json

@@ -0,0 +1,49 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.45.1",
+    "pytorch": "2.4.1"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null,
+  "query_prefix": "[unused0]",
+  "document_prefix": "[unused1]",
+  "query_length": 32,
+  "document_length": 180,
+  "attend_to_expansion_tokens": false,
+  "skiplist_words": [
+    "!",
+    "\"",
+    "#",
+    "$",
+    "%",
+    "&",
+    "'",
+    "(",
+    ")",
+    "*",
+    "+",
+    ",",
+    "-",
+    ".",
+    "/",
+    ":",
+    ";",
+    "<",
+    "=",
+    ">",
+    "?",
+    "@",
+    "[",
+    "\\",
+    "]",
+    "^",
+    "_",
+    "`",
+    "{",
+    "|",
+    "}",
+    "~"
+  ]
+}

convert_model.py

@@ -0,0 +1,25 @@
+from pylate import models
+# pip install pylate==1.1.2
+
+
+def get_pylate_model(language: str, train: bool) -> 'pylate.models.ColBERT':
+    """
+    Configures the antoinelouis/colbert-xm model for usage with PyLate
+    See discussion here: https://github.com/lightonai/pylate/discussions/50#discussioncomment-10691630
+    For language, use a code from https://huggingface.co/facebook/xmod-base#languages
+    """
+    colbert_model = models.ColBERT(model_name_or_path='antoinelouis/colbert-xm')
+    backbone = colbert_model[0].auto_model
+
+    if backbone.__class__.__name__.lower().startswith("xmod"):
+        backbone.set_default_language(language)
+
+        if train:
+            backbone.freeze_embeddings_and_language_adapters()
+
+    training = '' if not train else '_train'
+    colbert_model.save_pretrained(f'pylate-colbert-xm-{language}{training}/')
+
+
+if __name__ == '__main__':
+    get_pylate_model(language='de_DE', train=False)

model.md

@@ -0,0 +1,144 @@
+---
+base_model: antoinelouis/colbert-xm
+datasets: []
+language: []
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+widget: []
+---
+
+# SentenceTransformer based on antoinelouis/colbert-xm
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [antoinelouis/colbert-xm](https://huggingface.co/antoinelouis/colbert-xm). It maps sentences & paragraphs to a 128-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [antoinelouis/colbert-xm](https://huggingface.co/antoinelouis/colbert-xm) <!-- at revision f406563b621f86d96899d4652dfbc562692bb526 -->
+- **Maximum Sequence Length:** 514 tokens
+- **Output Dimensionality:** 128 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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
+
+```
+ColBERT(
+  (0): Transformer({'max_seq_length': 514, 'do_lower_case': False}) with Transformer model: XmodModel 
+  (1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+)
+```
+
+## 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
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 128]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.12.5
+- Sentence Transformers: 3.0.1
+- Transformers: 4.45.1
+- PyTorch: 2.4.1
+- Accelerate: 0.34.2
+- Datasets: 3.0.1
+- Tokenizers: 0.20.0
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b02095e5c4746382923f4c26caf58e2433a34134ef57a8f1ede723f4ef9cab
+size 3410427464

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Dense",
+    "type": "pylate.models.Dense"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 514,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "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": "<mask>",
+  "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 sha256:410ff101f2c7d6eb4f670a9410e9e27063dc10cd0c82fb1925ee779788d3036d
+size 17083106

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "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
+    },
+    "250002": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250003": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<mask>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}