feat: stage NLI-MiniLM2 experimental candidate

README.md

@@ -0,0 +1,20 @@
+---
+license: apache-2.0
+tags:
+  - onnx
+  - xberg
+---
+
+# Classification Models (experimental candidates)
+
+Unmodified copies of permissively licensed upstream ONNX exports, staged by [xberg](https://github.com/xberg-io/xberg) for evaluation (xberg-io/xberg#2334, #2336). **Experimental candidates, not qualified**: no model here is an xberg default, a supported preset or a bundling decision.
+
+| Directory | Upstream | Upstream revision | License | Task |
+|---|---|---|---|---|
+| `nli-minilm2-l6-h768` | [cross-encoder/nli-MiniLM2-L6-H768](https://huggingface.co/cross-encoder/nli-MiniLM2-L6-H768) | `b95119ce93d3e065de6214e38cd4a97b0f2f2c6d` | Apache-2.0 | zero-shot / NLI classification (3-way logits: 0 contradiction, 1 entailment, 2 neutral) |
+
+Every directory keeps the upstream `LICENSE` text (`LICENSE`), the upstream model card (`UPSTREAM_README.md`), tokenizer, processor and generation configuration, and all graphs the pipeline needs. `manifest.json` lists the SHA-256 and size of every file and the upstream revision it was copied from. Consumers must pin this repository's commit revision (recorded in `crates/xberg/src/candidate_models/`) and verify the SHA-256 values; do not resolve `main`.
+
+Attribution: each model remains the work of its upstream authors under the license listed above. Notes per model:
+
+- `nli-minilm2-l6-h768`: RoBERTa-tokenizer MiniLMv2 cross-encoder; fp32 plus arm64 qint8 and avx2 quint8 dynamic quantizations as published upstream. Base model nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large declares no license on its card (microsoft/unilm origin, MIT); the cross-encoder itself declares Apache-2.0.

manifest.json

@@ -0,0 +1,70 @@
+{
+  "note": "Experimental candidate artifacts, not qualified. Weights unmodified copies of the pinned upstream revisions; every file sha256-pinned.",
+  "models": {
+    "nli-minilm2-l6-h768": {
+      "upstream": "https://huggingface.co/cross-encoder/nli-MiniLM2-L6-H768",
+      "upstream_revision": "b95119ce93d3e065de6214e38cd4a97b0f2f2c6d",
+      "license": "Apache-2.0",
+      "task": "zero-shot / NLI classification (3-way logits: 0 contradiction, 1 entailment, 2 neutral)",
+      "notes": "RoBERTa-tokenizer MiniLMv2 cross-encoder; fp32 plus arm64 qint8 and avx2 quint8 dynamic quantizations as published upstream. Base model nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large declares no license on its card (microsoft/unilm origin, MIT); the cross-encoder itself declares Apache-2.0.",
+      "status": "experimental candidate, not qualified",
+      "files": [
+        {
+          "path": "nli-minilm2-l6-h768/LICENSE",
+          "sha256": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30",
+          "size_bytes": 11358
+        },
+        {
+          "path": "nli-minilm2-l6-h768/UPSTREAM_README.md",
+          "sha256": "1a6e3f880df3584acc1b209c7c667eb22cb7ddd98ab56a5905dda5cfc446ddd1",
+          "size_bytes": 2695
+        },
+        {
+          "path": "nli-minilm2-l6-h768/config.json",
+          "sha256": "8b0e41caff7567c0f53e6983f35591c3dec59507c9173ab125c5823394fb57f3",
+          "size_bytes": 875
+        },
+        {
+          "path": "nli-minilm2-l6-h768/merges.txt",
+          "sha256": "fe36cab26d4f4421ed725e10a2e9ddb7f799449c603a96e7f29b5a3c82a95862",
+          "size_bytes": 456356
+        },
+        {
+          "path": "nli-minilm2-l6-h768/model.onnx",
+          "sha256": "807d33fffefd95ad60e2a91f54eed50a92aa53c077945a6842bb587a49a3fdf3",
+          "size_bytes": 328649957
+        },
+        {
+          "path": "nli-minilm2-l6-h768/model_qint8_arm64.onnx",
+          "sha256": "449024a8711a3e655cad410cb2192158f9897fc2a32b65dbb817922351150db7",
+          "size_bytes": 82823065
+        },
+        {
+          "path": "nli-minilm2-l6-h768/model_quint8_avx2.onnx",
+          "sha256": "44391a5241a62e0083c1a8899a71e69a092b95aea5ba89e14062925468eceac7",
+          "size_bytes": 82823063
+        },
+        {
+          "path": "nli-minilm2-l6-h768/special_tokens_map.json",
+          "sha256": "378eb3bf733eb16e65792d7e3fda5b8a4631387ca04d2015199c4d4f22ae554d",
+          "size_bytes": 239
+        },
+        {
+          "path": "nli-minilm2-l6-h768/tokenizer.json",
+          "sha256": "82139106e603ee4e1d5bc99d056ccbed5a92bc24848b1b5a7137c26e00d0dbf6",
+          "size_bytes": 1356048
+        },
+        {
+          "path": "nli-minilm2-l6-h768/tokenizer_config.json",
+          "sha256": "e06f5c3c435fc0255b08b5574cd574eec685390f60c85b27f83d785eb8ecaaa1",
+          "size_bytes": 330
+        },
+        {
+          "path": "nli-minilm2-l6-h768/vocab.json",
+          "sha256": "ed19656ea1707df69134c4af35c8ceda2cc9860bf2c3495026153a133670ab5e",
+          "size_bytes": 798293
+        }
+      ]
+    }
+  }
+}

nli-minilm2-l6-h768/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.

nli-minilm2-l6-h768/UPSTREAM_README.md

@@ -0,0 +1,69 @@
+---
+language: en
+pipeline_tag: zero-shot-classification
+tags:
+- transformers
+datasets:
+- nyu-mll/multi_nli
+- stanfordnlp/snli
+metrics:
+- accuracy
+license: apache-2.0
+base_model:
+- nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large
+library_name: sentence-transformers
+---
+
+# Cross-Encoder for Natural Language Inference
+This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
+
+## Training Data
+The model was trained on the [SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral.
+
+## Performance
+For evaluation results, see [SBERT.net - Pretrained Cross-Encoder](https://www.sbert.net/docs/pretrained_cross-encoders.html#nli).
+
+## Usage
+
+Pre-trained models can be used like this:
+```python
+from sentence_transformers import CrossEncoder
+model = CrossEncoder('cross-encoder/nli-MiniLM2-L6-H768')
+scores = model.predict([('A man is eating pizza', 'A man eats something'), ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')])
+
+#Convert scores to labels
+label_mapping = ['contradiction', 'entailment', 'neutral']
+labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]
+```
+
+## Usage with Transformers AutoModel
+You can use the model also directly with Transformers library (without SentenceTransformers library):
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/nli-MiniLM2-L6-H768')
+tokenizer = AutoTokenizer.from_pretrained('cross-encoder/nli-MiniLM2-L6-H768')
+
+features = tokenizer(['A man is eating pizza', 'A black race car starts up in front of a crowd of people.'], ['A man eats something', 'A man is driving down a lonely road.'],  padding=True, truncation=True, return_tensors="pt")
+
+model.eval()
+with torch.no_grad():
+    scores = model(**features).logits
+    label_mapping = ['contradiction', 'entailment', 'neutral']
+    labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
+    print(labels)
+```
+
+## Zero-Shot Classification
+This model can also be used for zero-shot-classification:
+```python
+from transformers import pipeline
+
+classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-MiniLM2-L6-H768')
+
+sent = "Apple just announced the newest iPhone X"
+candidate_labels = ["technology", "sports", "politics"]
+res = classifier(sent, candidate_labels)
+print(res)
+```

nli-minilm2-l6-h768/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "contradiction",
+    "1": "entailment",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 0,
+    "entailment": 1,
+    "neutral": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

nli-minilm2-l6-h768/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807d33fffefd95ad60e2a91f54eed50a92aa53c077945a6842bb587a49a3fdf3
+size 328649957

nli-minilm2-l6-h768/model_qint8_arm64.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449024a8711a3e655cad410cb2192158f9897fc2a32b65dbb817922351150db7
+size 82823065

nli-minilm2-l6-h768/model_quint8_avx2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44391a5241a62e0083c1a8899a71e69a092b95aea5ba89e14062925468eceac7
+size 82823063

nli-minilm2-l6-h768/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

nli-minilm2-l6-h768/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large"}