Add baa.ai Embedding-Reranker-Arctic-L-RerankerV2M3-v1 (unified shared word-emb)

.gitattributes

@@ -33,3 +33,5 @@ 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
+embedder/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+reranker/tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

NOTICE

@@ -0,0 +1,27 @@
+baa.ai · Embedding-Reranker-Arctic-L-RerankerV2M3-v1
+Copyright (c) 2026 baa.ai
+
+This product is a derivative work licensed under the Apache License, Version 2.0.
+It re-packages and modifies the following upstream models:
+
+  1. Snowflake/snowflake-arctic-embed-l-v2.0  (license: Apache-2.0)
+       Used as the bi-encoder embedder. Provides the canonical (shared)
+       word-embedding table for the combined model.
+       https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0
+
+  2. BAAI/bge-reranker-v2-m3  (license: Apache-2.0)
+       Used as the cross-encoder reranker. Its word-embedding table has been
+       removed on disk and is injected at load time from the shared table
+       above, reducing the combined footprint.
+       https://huggingface.co/BAAI/bge-reranker-v2-m3
+
+Both upstream models derive from the XLM-RoBERTa-large architecture.
+
+Modifications by baa.ai:
+  - Unified the two models into a single artifact over one shared
+    word-embedding table (the reranker's word-embedding matrix is stored
+    once, in the embedder, and injected at load).
+  - Added a combined loader (modeling_baa.py) exposing embed() and rerank().
+
+This NOTICE file is provided in accordance with Section 4(d) of the
+Apache License, Version 2.0. See the LICENSE file for the full license text.

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- retrieval
+- embeddings
+- reranker
+- cross-encoder
+- rag
+- sentence-similarity
+pipeline_tag: sentence-similarity
+---
+
+# baa.ai · Embedding-Reranker-Arctic-L-RerankerV2M3-v1
+
+**A single model that does both halves of RAG retrieval — bi-encoder embedding *and* cross-encoder reranking — over one shared word-embedding table.**
+
+The embedder and reranker share their word-embedding table (stored once), so the packaged model is **~22.5% smaller on disk than shipping the two components separately**, with **no measured loss in retrieval quality**.
+
+## Why this model
+
+Most RAG stacks bolt an embedder onto a reranker and pay for both. A well-matched embedder + reranker that share a backbone recover the right documents just as well — in a single, smaller download.
+
+- **Two jobs, one download** — embed for retrieval, then rerank the candidates.
+- **Smaller footprint** — the shared word-embedding table is stored once.
+- **Strong default** — a sensible starting point for production RAG.
+
+## Usage
+
+```python
+from modeling_baa import BaaEmbeddingReranker   # included in this repo
+
+m = BaaEmbeddingReranker("baa-ai/Embedding-Reranker-Arctic-L-RerankerV2M3-v1")
+qv = m.embed(["how does a cross-encoder reranker work?"], is_query=True)[0]
+dv = m.embed(["a cross-encoder scores a (query, document) pair jointly",
+              "bi-encoders embed query and document separately for fast retrieval"])
+ranked = m.rerank("how does a cross-encoder reranker work?",
+                  ["a cross-encoder scores a (query, document) pair jointly",
+                   "the mitochondria is the powerhouse of the cell"])
+# -> [(doc, score), ...] sorted best-first
+```
+
+## Get the optimal models for *your* data
+
+This model is a great **default**. But the best embedder and reranker are **corpus-specific**. **baa.ai offers exclusive tooling that identifies the optimal embedding and reranking models for your specific data** — if you want that tailored recommendation, **reach out to baa.ai**.
+
+## Specs
+
+| | |
+|---|---|
+| Embedding dim | 1024 |
+| Vocab | 250002 |
+| Max sequence length | 512 |
+| Combined params | ~879.5M (vs ~1135.5M separate) |
+| Footprint vs separate models | ~22.5% smaller on disk, no measured quality loss |
+| Hardware | CPU / edge / GPU |
+
+## License & attribution
+
+Released under the **Apache License 2.0**. Derivative work re-packaging two upstream models into a single shared-backbone artifact (see `NOTICE`):
+- `Snowflake/snowflake-arctic-embed-l-v2.0` (embedder)
+- `BAAI/bge-reranker-v2-m3` (reranker)
+
+© baa.ai. Provided "as is" without warranty; see `LICENSE`.

config.json

@@ -0,0 +1,23 @@
+{
+  "model_type": "baa-embed-rerank",
+  "description": "Unified bi-encoder embedder + cross-encoder reranker sharing one word-embedding table.",
+  "components": {
+    "embedder": "embedder/",
+    "reranker": "reranker/"
+  },
+  "loader": "modeling_baa.BaaEmbeddingReranker",
+  "embed_query_prompt": "query: ",
+  "embed_doc_prompt": "",
+  "embedding_dim": 1024,
+  "vocab_size": 250002,
+  "max_seq_length": 512,
+  "separate_params_millions": 1135.5,
+  "combined_params_millions": 879.5,
+  "disk_saving_pct": 22.5,
+  "license": "apache-2.0",
+  "trust_remote_code": true,
+  "upstream": {
+    "embedder": "Snowflake/snowflake-arctic-embed-l-v2.0",
+    "reranker": "BAAI/bge-reranker-v2-m3"
+  }
+}

embedder/1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 1024,
+    "pooling_mode": "cls",
+    "include_prompt": true
+}

embedder/config.json

@@ -0,0 +1,33 @@
+{
+  "add_cross_attention": false,
+  "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,
+  "is_decoder": false,
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

embedder/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.12.1",
+    "sentence_transformers": "5.6.0",
+    "transformers": "5.12.1"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "",
+    "query": "query: "
+  },
+  "similarity_fn_name": "cosine"
+}

embedder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bf1a120b1c6562aeec379dfa9039b0d360591c784cb1c6786e87256b738ee1
+size 2271064456

embedder/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.sentence_transformer.modules.normalize.Normalize"
+  }
+]

embedder/sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

embedder/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

embedder/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "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>"
+}

modeling_baa.py

@@ -0,0 +1,83 @@
+"""baa.ai unified Embedding+Reranker loader (generic).
+
+A single artifact that does both halves of RAG retrieval — bi-encoder embedding AND cross-encoder reranking —
+over ONE shared word-embedding table. The reranker's word-embedding matrix is stored only once (in the
+embedder) and injected at load, so the packaged model is smaller than shipping the two components separately,
+at no measured quality cost.
+
+Works for BERT-based and XLM-RoBERTa-based stacks alike: the reranker's encoder submodule is resolved
+generically via `reranker.base_model` (so `.bert` / `.roberta` are both handled). Optional per-model query/doc
+prompts are read from config.json (e.g. arctic uses "query: ").
+
+Usage:
+    from modeling_baa import BaaEmbeddingReranker
+    m = BaaEmbeddingReranker("path/to/model-dir")
+    qv = m.embed(["what is a cross-encoder?"], is_query=True)         # normalized bi-encoder vectors
+    dv = m.embed(["a cross-encoder scores a (query, doc) pair jointly"])
+    ranked = m.rerank("what is a cross-encoder?", ["doc A ...", "doc B ..."])   # [(doc, score), ...] desc
+"""
+import os, json, torch
+from safetensors.torch import load_file
+from sentence_transformers import SentenceTransformer
+from transformers import AutoConfig, AutoModelForSequenceClassification, AutoTokenizer
+
+
+class BaaEmbeddingReranker:
+    def __init__(self, path=None, device=None):
+        path = path or os.path.dirname(os.path.abspath(__file__))
+        self.device = device or ("mps" if torch.backends.mps.is_available()
+                                 else ("cuda" if torch.cuda.is_available() else "cpu"))
+        cfg = {}
+        cfg_path = os.path.join(path, "config.json")
+        if os.path.exists(cfg_path):
+            cfg = json.load(open(cfg_path))
+        self.q_prompt = cfg.get("embed_query_prompt", "") or ""
+        self.d_prompt = cfg.get("embed_doc_prompt", "") or ""
+        trc = bool(cfg.get("trust_remote_code", False))
+        emb_dir, rr_dir = os.path.join(path, "embedder"), os.path.join(path, "reranker")
+
+        # embedder = bi-encoder; holds the canonical shared word-embedding table
+        self.embedder = SentenceTransformer(emb_dir, device=self.device, trust_remote_code=trc)
+        shared_wemb = self.embedder[0].auto_model.embeddings.word_embeddings.weight.data
+
+        # reranker = cross-encoder seq-classifier; word-embedding stripped on disk -> injected from shared table
+        rr_cfg = AutoConfig.from_pretrained(rr_dir, trust_remote_code=trc)
+        self.reranker = AutoModelForSequenceClassification.from_config(rr_cfg, trust_remote_code=trc)
+        self.reranker.load_state_dict(load_file(os.path.join(rr_dir, "model.safetensors")), strict=False)
+        # resolve the encoder submodule generically (.bert for BERT, .roberta for XLM-R, ...)
+        base = self.reranker.base_model
+        base.embeddings.word_embeddings.weight.data = shared_wemb.to(self.reranker.dtype).clone()
+        self.reranker.to(self.device).eval()
+        self.rr_tok = AutoTokenizer.from_pretrained(rr_dir, trust_remote_code=trc)
+
+    def embed(self, texts, is_query=False, batch_size=32):
+        """Return L2-normalized bi-encoder vectors. Applies the model's query/doc prompt if configured."""
+        prompt = self.q_prompt if is_query else self.d_prompt
+        texts = [prompt + t for t in texts] if prompt else list(texts)
+        return self.embedder.encode(texts, normalize_embeddings=True,
+                                    batch_size=batch_size, show_progress_bar=False)
+
+    @torch.no_grad()
+    def rerank(self, query, docs, top_k=None, batch_size=32):
+        """Cross-encoder relevance scores for (query, doc) pairs; returns [(doc, score), ...] sorted desc."""
+        scores = []
+        for i in range(0, len(docs), batch_size):
+            enc = self.rr_tok([(query, d[:2000]) for d in docs[i:i + batch_size]], padding=True,
+                              truncation=True, max_length=512, return_tensors="pt").to(self.device)
+            scores.extend(self.reranker(**enc).logits[:, 0].float().cpu().tolist())
+        order = sorted(range(len(docs)), key=lambda j: -scores[j])
+        if top_k:
+            order = order[:top_k]
+        return [(docs[j], scores[j]) for j in order]
+
+
+if __name__ == "__main__":
+    import numpy as np
+    m = BaaEmbeddingReranker()
+    q = "How does a cross-encoder reranker work?"
+    docs = ["A cross-encoder jointly encodes the query and document to score relevance.",
+            "The mitochondria is the powerhouse of the cell.",
+            "Bi-encoders embed query and document separately for fast retrieval."]
+    qv = m.embed([q], is_query=True)[0]; dv = m.embed(docs)
+    print("embed cos:", [round(float(np.dot(qv, d)), 3) for d in dv])
+    print("rerank   :", [(round(s, 2), d[:45]) for d, s in m.rerank(q, docs)])

reranker/config.json

@@ -0,0 +1,36 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

reranker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1666adf94fd3e60bb127998660adac7591ebb8677d2e30bd1c18940e1a10477c
+size 1247062844

reranker/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df1f55d60c9705a501ab9a75550728625740741fe4be308dac4806c16b7d51d
+size 17098085

reranker/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}