Rebrand to baa.ai Merino-XL-v2 (backbone-only attribution)

LICENSE

@@ -1,202 +1,24 @@
-
-                                 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.
+Merino-XL-v2 — Proprietary License
+Copyright (c) 2026 BAA AI (Black Sheep AI). All rights reserved.
+
+1. SCOPE. This license governs the "BAA Contributions" in this package: the
+   shared word-embedding architecture and configuration, the router / loader
+   code (modeling_baa.py), the model packaging, BAA AI's weight contributions,
+   the model card, and associated documentation.
+
+2. GRANT. No right to use, reproduce, modify, distribute, sublicense, or create
+   derivative works of the BAA Contributions is granted except under a separate
+   written agreement with BAA AI (Black Sheep AI).
+
+3. THIRD-PARTY COMPONENT. This package incorporates the xlm-roberta-large backbone,
+   provided under the MIT License — see LICENSE-xlm-roberta-large.txt. The MIT terms govern that
+   backbone component only; nothing in this license limits any rights you have
+   under the MIT License with respect to it.
+
+4. NO WARRANTY. THE PACKAGE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+   EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO MERCHANTABILITY, FITNESS FOR
+   A PARTICULAR PURPOSE, AND NONINFRINGEMENT. IN NO EVENT SHALL BAA AI BE LIABLE
+   FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY ARISING FROM OR IN CONNECTION WITH
+   THE PACKAGE OR ITS USE.
+
+Contact: BAA AI (Black Sheep AI) — baa.ai

LICENSE-xlm-roberta-large.txt

@@ -0,0 +1,23 @@
+Backbone component: xlm-roberta-large — MIT License
+
+MIT License
+
+Copyright (c) Facebook, Inc. and its affiliates.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MODEL_CARD.md

@@ -0,0 +1,61 @@
+---
+license: other
+license_name: baa-proprietary
+library_name: sentence-transformers
+tags:
+- retrieval
+- embeddings
+- reranker
+- cross-encoder
+- rag
+- sentence-similarity
+pipeline_tag: sentence-similarity
+---
+
+# baa.ai · Merino-XL-v2
+
+**One model that does both halves of RAG retrieval — bi-encoder embedding *and* cross-encoder reranking — over a single shared word-embedding table.** A 1024-dimensional multilingual model, ~880M parameters, by BAA AI (Black Sheep AI).
+
+## Get the optimal model for *your* data
+
+Merino-XL-v2 is a strong, cost-efficient **default**. But the best embedder + reranker is **corpus-specific** — the ideal choice depends on your documents and your notion of relevance. **baa.ai offers exclusive tooling that identifies the optimal embedding and reranking models for your specific data**, so you ship the smallest models that maximize document recovery on your corpus. For a tailored recommendation, **reach out to baa.ai**.
+
+## What it is
+
+A two-role retrieval model over a **shared input word-embedding matrix** (stored once). The bi-encoder embedder and a v2 cross-encoder reranker are built on the same `xlm-roberta-large` backbone, so their word-embedding table is stored a single time and injected into the reranker at load — a smaller download at **no measured quality loss**, with no retraining.
+
+- **Embed role:** bi-encoder, 1024-d, L2-normalized. Prepend `"query: "` to queries.
+- **Rerank role:** cross-encoder, single relevance logit per (query, document) pair.
+- **Router:** call `.embed(...)` or `.rerank(...)`.
+
+## Usage
+
+```python
+from modeling_baa import BaaEmbeddingReranker   # included in this repo
+
+m = BaaEmbeddingReranker("baa-ai/Merino-XL-v2")
+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
+```
+
+## Specs
+
+| | |
+|---|---|
+| Embedding dim | 1024 |
+| Parameters | ~880M (embedder + reranker, shared word-embedding table) |
+| Languages | multilingual |
+| Max sequence length | 512 |
+| Hardware | CPU / edge / GPU |
+
+## License & attribution
+
+- **BAA Contributions** (shared-embedding architecture, router/loader code, packaging, weights, docs) are **proprietary to BAA AI (Black Sheep AI)** — see `LICENSE`.
+- Incorporates the `xlm-roberta-large` backbone under the **MIT License** — see `LICENSE-xlm-roberta-large.txt`.
+
+© 2026 BAA AI (Black Sheep AI) — baa.ai. Provided "as is" without warranty.

NOTICE

@@ -1,27 +1,5 @@
-baa.ai · Embedding-Reranker-Arctic-L-RerankerV2M3-v1
-Copyright (c) 2026 baa.ai
+Merino-XL-v2
+Copyright (c) 2026 BAA AI (Black Sheep AI). All rights reserved.
 
-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.
+BAA Contributions: proprietary — see LICENSE.
+Backbone: xlm-roberta-large — MIT License — see LICENSE-xlm-roberta-large.txt.

README.md

@@ -1,5 +1,6 @@
 ---
-license: apache-2.0
+license: other
+license_name: baa-proprietary
 library_name: sentence-transformers
 tags:
 - retrieval
@@ -11,26 +12,28 @@ tags:
 pipeline_tag: sentence-similarity
 ---
 
-# baa.ai · Embedding-Reranker-Arctic-L-RerankerV2M3-v1
+# baa.ai · Merino-XL-v2
 
-**A single model that does both halves of RAG retrieval — bi-encoder embedding *and* cross-encoder reranking — over one shared word-embedding table.**
+**One model that does both halves of RAG retrieval — bi-encoder embedding *and* cross-encoder reranking — over a single shared word-embedding table.** A 1024-dimensional multilingual model, ~880M parameters, by BAA AI (Black Sheep AI).
 
-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**.
+## Get the optimal model for *your* data
 
-## Why this model
+Merino-XL-v2 is a strong, cost-efficient **default**. But the best embedder + reranker is **corpus-specific** — the ideal choice depends on your documents and your notion of relevance. **baa.ai offers exclusive tooling that identifies the optimal embedding and reranking models for your specific data**, so you ship the smallest models that maximize document recovery on your corpus. For a tailored recommendation, **reach out to baa.ai**.
 
-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.
+## What it is
 
-- **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.
+A two-role retrieval model over a **shared input word-embedding matrix** (stored once). The bi-encoder embedder and a v2 cross-encoder reranker are built on the same `xlm-roberta-large` backbone, so their word-embedding table is stored a single time and injected into the reranker at load — a smaller download at **no measured quality loss**, with no retraining.
+
+- **Embed role:** bi-encoder, 1024-d, L2-normalized. Prepend `"query: "` to queries.
+- **Rerank role:** cross-encoder, single relevance logit per (query, document) pair.
+- **Router:** call `.embed(...)` or `.rerank(...)`.
 
 ## Usage
 
 ```python
 from modeling_baa import BaaEmbeddingReranker   # included in this repo
 
-m = BaaEmbeddingReranker("baa-ai/Embedding-Reranker-Arctic-L-RerankerV2M3-v1")
+m = BaaEmbeddingReranker("baa-ai/Merino-XL-v2")
 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"])
@@ -40,25 +43,19 @@ ranked = m.rerank("how does a cross-encoder reranker work?",
 # -> [(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 |
+| Parameters | ~880M (embedder + reranker, shared word-embedding table) |
+| Languages | multilingual |
 | 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 Contributions** (shared-embedding architecture, router/loader code, packaging, weights, docs) are **proprietary to BAA AI (Black Sheep AI)** — see `LICENSE`.
+- Incorporates the `xlm-roberta-large` backbone under the **MIT License** — see `LICENSE-xlm-roberta-large.txt`.
 
-© baa.ai. Provided "as is" without warranty; see `LICENSE`.
+© 2026 BAA AI (Black Sheep AI) — baa.ai. Provided "as is" without warranty.

config.json

@@ -1,23 +1,15 @@
 {
-  "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",
+  "model_type": "baa-embedding-reranker",
+  "name": "Merino-XL-v2",
+  "version": "1",
+  "license": "Proprietary \u2014 BAA AI (Black Sheep AI); xlm-roberta-large backbone under MIT",
+  "architecture": "shared-word-embedding: one xlm-roberta-large word-embedding table shared across the embedder and reranker stacks",
+  "embedding_dim": 1024,
   "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",
+  "params_millions": 880,
+  "backbone": "xlm-roberta-large (MIT)",
   "trust_remote_code": true,
-  "upstream": {
-    "embedder": "Snowflake/snowflake-arctic-embed-l-v2.0",
-    "reranker": "BAAI/bge-reranker-v2-m3"
-  }
+  "loader": "modeling_baa.BaaEmbeddingReranker"
 }

modeling_baa.py

@@ -7,7 +7,7 @@ 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: ").
+prompts are read from config.json (e.g. some models use a "query: " prefix).
 
 Usage:
     from modeling_baa import BaaEmbeddingReranker
@@ -49,6 +49,10 @@ class BaaEmbeddingReranker:
         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)
+        # Weights may be stored fp16 on disk (smaller artifact); CPU can't compute in half -> upcast to fp32.
+        if str(self.device) == "cpu":
+            self.embedder = self.embedder.to(torch.float32)
+            self.reranker = self.reranker.float()
 
     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."""