Upload folder using huggingface_hub

.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 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
+    "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

@@ -0,0 +1,79 @@
+---
+language:
+- en
+- multilingual
+license: apache-2.0
+tags:
+- sentence-transformers
+- embedding
+- ror
+- affiliation-matching
+- contrastive-learning
+base_model: Snowflake/snowflake-arctic-embed-l-v2.0
+datasets:
+- SIRIS-Lab/affilgood-contrastive-dataset
+pipeline_tag: sentence-similarity
+---
+
+# Snowflake Arctic Embeddings for ROR Affiliation Matching
+
+A sentence embedding model fine-tuned for Research Organization Registry (ROR) affiliation matching.
+
+## Model Description
+
+This model is fine-tuned from `Snowflake/snowflake-arctic-embed-l-v2.0` using contrastive learning
+on the AffilGood contrastive dataset. It produces embeddings optimized for matching affiliation
+strings to ROR organization records.
+
+## Training
+
+- **Base model**: Snowflake/snowflake-arctic-embed-l-v2.0
+- **Training dataset**: SIRIS-Lab/affilgood-contrastive-dataset
+- **Training examples**: 50,255
+- **Validation examples**: 2,645
+- **Loss**: MultipleNegativesRankingLoss (with hard negatives)
+- **Epochs**: 3
+- **Batch size**: 32
+- **Learning rate**: 2e-05
+- **Max sequence length**: 256
+
+## Usage
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("cometadata/snowflake-arctic-ror-affiliations")
+
+# Encode affiliations
+affiliations = [
+    "Department of Physics, MIT, Cambridge, MA",
+    "Harvard Medical School, Boston",
+]
+embeddings = model.encode(affiliations, normalize_embeddings=True)
+
+# Encode ROR organization names for matching
+organizations = [
+    "Massachusetts Institute of Technology",
+    "Harvard University",
+]
+org_embeddings = model.encode(organizations, normalize_embeddings=True)
+
+# Compute similarity
+import numpy as np
+similarities = np.dot(embeddings, org_embeddings.T)
+```
+
+## Intended Use
+
+This model is designed for dense retrieval in affiliation matching pipelines.
+It should be used as the first-stage retriever to find candidate ROR organizations
+for a given affiliation string.
+
+## Training Data
+
+Fine-tuned on [SIRIS-Lab/affilgood-contrastive-dataset](https://huggingface.co/datasets/SIRIS-Lab/affilgood-contrastive-dataset),
+which contains 52,900 affiliation-organization pairs with curated hard negatives across 105 languages.
+
+## Timestamp
+
+2026-01-07T08:08:33.561241+00:00

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "matryoshka_dimensions": [
+    256
+  ],
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.57.3",
+    "pytorch": "2.9.1+cu128"
+  },
+  "prompts": {
+    "query": "query: ",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7f1e99ae40870009666671be714c1b0115080383b566689c838d4b27305500
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 256,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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:b8cd58c3e5a595b5f311ecf453cd69a9468b128efe720b707a331b8f748fdd75
+size 17083052

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}