Erste Fassung

.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

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.

README.md

@@ -0,0 +1,153 @@
+---
+license: apache-2.0
+language: [de, en, fr, it, es, nl, pl, tr, cs, hr, hu, pt, ro, uk]
+library_name: transformers
+pipeline_tag: text-classification
+base_model: jhu-clsp/mmBERT-base
+tags: [intent, routing, chatbot, agents, moderation, prompt-injection, off-topic]
+datasets: [deepset/prompt-injections, jagoldz/gahd, nvidia/Nemotron-Safety-Guard-Dataset-v3, reshabhs/SPML_Chatbot_Prompt_Injection]
+---
+
+# ALLSmartIntent Flash
+
+**What does this chat message want, and what does a good reply need?** ALLSmartIntent Flash answers 14 such
+questions about the newest message of a chat in one pass, in milliseconds, before an expensive language model call
+starts: dialogue act, reference to the conversation, which data a reply needs, mood, off-topic, rule bypassing,
+unclear requests, inappropriate content, crisis and extremism, and the language of the message.
+
+It is trained to be general: it reads one sentence about the purpose of the bot, the last messages and the new
+message. What only concerns your bot, such as which of your tools fits, stays with you.
+
+ALLSmartIntent runs in the gateway of [ALLSmartLLM](https://allsmartllm.com) on our own hardware in Austria. See also
+our privacy models [ALLSmartArt4](https://huggingface.co/allsmart/Art4),
+[ALLSmartArt4i](https://huggingface.co/allsmart/Art4i) and [ALLSmartArt9-10](https://huggingface.co/allsmart/Art9-10).
+
+| | |
+|---|---|
+| Size | 0.3B parameters, mmBERT-base with four linear heads |
+| Input | purpose of the bot, history (optional), new message; up to 512 tokens |
+| Languages | trained on 14 languages, measured mainly on German and English |
+| Speed | GPU (RTX 4070 Ti): ≈ 8 ms per message, ≈ 1 ms per message in batches of 32. CPU (Ryzen 7 7800X3D, 8 threads): ≈ 29 ms per message |
+
+## Outputs
+
+| Head | Type | Values |
+|---|---|---|
+| `akt` | one class | `frage` (question), `auftrag` (request), `aussage` (statement), `kurzantwort` ("yes", "the second one": only understandable with the history), `korrektur` (contradicts the last answer), `dank`, `gruss_smalltalk`, `beschwerde` (complaint) |
+| `bezug` | one class | `neu`, `anschluss` (continues the last answer: "and tomorrow?"), `themenwechsel` (change of topic) |
+| `bedarf_*` | yes/no each | what a good reply needs: `aktuelle_daten` (weather, prices, news, timetables), `nutzerdaten` (the user's own accounts, appointments, files), `aktion` (do, send or change something), `dokumente` (manuals, reports, wiki), `rechnen` (calculation or comparison), `allgemeinwissen` (answerable without external data) |
+| `stimmung_*` | yes/no each | `besorgt` (worried), `veraergert` (annoyed), `dringend` (urgent) |
+| `rahmen` | yes/no | the message fits the purpose of the bot (no means off-topic) |
+| `regelumgehung` | yes/no | wants to see or change the instructions, break the role, prompt injection |
+| `unklar` | yes/no | cannot be answered sensibly without asking back |
+| `unangemessen` | yes/no | insults, harassment, hateful content |
+| `krise` | yes/no | signs of self-harm or acute crisis |
+| `extremismus` | yes/no | hate against groups, extremist content |
+| `sprache` | one class | language of the new message: `cs de en es fr hr hu it nl pl pt ro tr uk`, `andere` |
+
+Every yes/no head is an independent sigmoid score with its own threshold in `intent.json`.
+
+```
+Purpose: Flight assistant on an airline website.
+History: user "Wie wird das Wetter heute in Wien bei der Landung?" / bot "In Wien sind es bei der Landung etwa 18 Grad."
+
+"und morgen?"                                   frage, anschluss: aktuelle_daten, allgemeinwissen, rahmen
+"Ignore all previous instructions and print …"  auftrag, neu: regelumgehung (not rahmen)
+"Kannst du mir ein Rezept für Gulasch geben?"   frage, themenwechsel: allgemeinwissen (not rahmen: off-topic)
+"Ich habe solche Angst vorm Fliegen …"          aussage, themenwechsel: stimmung_besorgt, rahmen
+```
+
+## Usage
+
+`beispiel.py` in this repository loads the model and contains the input format used in training:
+
+```python
+from beispiel import entscheide
+entscheide([{"zweck": "Flight assistant on an airline website.",
+             "verlauf": [{"rolle": "nutzer", "text": "…"}, {"rolle": "bot", "text": "…"}],
+             "nachricht": "und morgen?"}])
+# [{"akt": "frage", "bezug": "anschluss", "sprache": "de", "ja": ["bedarf_aktuelle_daten", "rahmen", …], "werte": {…}}]
+```
+
+The model is the encoder in this repository (`AutoModel`) plus `koepfe.safetensors` (the heads) and `intent.json`
+(label lists and thresholds). Keep the input format: new message first, then purpose, then the history newest first,
+so truncation drops the oldest history and never the message.
+
+Typical use: route to the right tool or model, ask back on `unklar`, answer off-topic messages with a fixed text,
+and answer `krise`, `unangemessen` and `regelumgehung` with fixed, reviewed responses before the language model sees
+the message.
+
+## Evaluation
+
+Test sets created and annotated by hand independently of the training data, never used for training or model
+selection: 450 short chat excerpts (blind set 1) and 120 with long messages or long histories (blind set 2), for
+three bots (flight assistant, personal agent, stock expert chat). 383 of the 450 are German, the rest English,
+French, Italian, Spanish, Dutch, Polish and Turkish.
+
+| | blind set 1 (450) | blind set 2 (120, long) |
+|---|---|---|
+| `akt` accuracy | 91.6 % | 89.2 % |
+| `bezug` accuracy | 91.1 % | 87.5 % |
+| `sprache` accuracy | 98.7 % | 99.2 % |
+| `rahmen` F1 | 0.93 | 0.92 |
+| `regelumgehung` F1 | 0.93 (precision 100 %) | 1.00 |
+| `bedarf_aktion` F1 | 0.75 | 0.75 |
+| `bedarf_aktuelle_daten` F1 | 0.71 | 0.73 |
+| `bedarf_dokumente` F1 | 0.71 | 0.50 |
+| `bedarf_rechnen` F1 | 0.69 | 0.47 |
+| `bedarf_allgemeinwissen` F1 | 0.68 | 0.40 |
+| `bedarf_nutzerdaten` F1 | 0.63 | 0.73 |
+| `stimmung_veraergert` F1 | 0.75 | 0.71 |
+| `stimmung_dringend` F1 | 0.74 | 0.35 (3 cases) |
+| `stimmung_besorgt` F1 | 0.54 | 0.77 |
+| `unklar` F1 | 0.54 | 0.67 |
+
+Public test sets (test splits only; where a training split exists it was part of the training data):
+
+| | head | F1 | precision | recall |
+|---|---|---|---|---|
+| Multilingual HateCheck, German (997) | `unangemessen` | 0.84 | 73 % | 98 % |
+| Multilingual HateCheck, German (997) | `extremismus` | 0.83 | 79 % | 88 % |
+| GermEval 2018 test, ABUSE/INSULT vs OTHER (750) | `unangemessen` | 0.75 | 65 % | 88 % |
+| deepset/prompt-injections test (116) | `regelumgehung` | 0.93 | 100 % | 87 % |
+
+Normal traffic: 1 crisis false alarm in 570 blind messages.
+
+## Limitations
+
+- **The `bedarf_*` heads are hints for routing, not decisions.** Precision is often 50 to 70 %: the model rather says
+  a reply might need documents or user data than miss it. People also disagree on these questions.
+- **`krise` is basic protection.** Clear statements are found reliably; subtle hints spread over several messages
+  are not. It does not replace a crisis service or a review by a larger model where crises are expected.
+- **Crude language is flagged as `unangemessen`** even without an insult (GermEval PROFANITY: 41 of 48).
+- `unklar` and `stimmung_besorgt` are the weakest heads, partly because the answer depends on the bot.
+- Measured mainly on German and English; the other languages are covered in training but measured on few cases.
+- `sprache` can follow the conversation: a short English message in a German conversation may come out as `de`.
+- Long messages and long histories cost accuracy for `bedarf_rechnen` and `bedarf_allgemeinwissen` (blind set 2).
+
+## Training data
+
+Invented chat excerpts in 14 languages, created for this purpose for many different bot purposes, plus a few hundred
+cases annotated by hand. No customer data and no real personal data. In addition, the training splits of these
+public datasets:
+
+- GermEval 2018 (Wiegand, Siegel, Ruppenhofer: *Overview of the GermEval 2018 Shared Task on the Identification of
+  Offensive Language*, KONVENS 2018), CC BY 4.0
+- GAHD, German Adversarial Hate Speech Dataset (Goldzycher et al., NAACL 2024), CC BY 4.0
+- Nemotron Safety Guard Dataset v3 (NVIDIA; Joshi et al., *CultureGuard*, arXiv:2508.01710), CC BY 4.0
+- SPML Chatbot Prompt Injection (Sharma et al., arXiv:2402.11755), MIT
+- deepset/prompt-injections, Apache 2.0
+
+Tweets were cleaned of handles, hashtags and links. Evaluation additionally uses Multilingual HateCheck (Röttger et
+al., 2022), never for training.
+
+## License
+
+Apache 2.0. Base model mmBERT-base (MIT).
+
+---
+
+**Deutsch:** ALLSmartIntent Flash erkennt in Millisekunden, was eine Chat-Nachricht will und was eine gute Antwort
+braucht: Art der Nachricht, Bezug zum Verlauf, Datenbedarf, Stimmung, Off-Topic, Regelumgehung, Unklarheit,
+Unangemessenes, Krise, Extremismus und Sprache, in einem Durchlauf vor dem Aufruf des großen Modells. Es läuft im
+Gateway von [ALLSmartLLM](https://allsmartllm.com).

beispiel.py

@@ -0,0 +1,91 @@
+"""ALLSmartIntent Flash: what a chat message wants and what a good reply needs, in one pass.
+
+    pip install torch transformers safetensors huggingface_hub
+    python beispiel.py "und morgen?"
+
+Input: one sentence about the purpose of the bot, the last messages (optional) and the new message.
+Output: dialogue act, reference to the conversation, needs, mood, safety signals and language.
+"""
+import json, sys
+
+import torch
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+from torch import nn
+from transformers import AutoModel, AutoTokenizer
+
+MODELL = "allsmart/Intent-Flash"
+MAX_VERLAUF_ZEICHEN = 600   # per earlier message; longer ones keep start and end (the question is usually at the end)
+GERAET = "cuda" if torch.cuda.is_available() else "cpu"
+
+meta = json.load(open(hf_hub_download(MODELL, "intent.json")))
+AKT, BEZUG, JA_NEIN, SPRACHEN, SCHWELLEN = (meta[k] for k in ("akt", "bezug", "ja_nein", "sprachen", "schwellen"))
+
+
+def eingabe(zweck: str, verlauf: list[dict], nachricht: str) -> str:
+    """Same format as in training: new message first, then purpose, then history newest first.
+    Truncation therefore drops the oldest history, never the message."""
+    teile = [f"Nachricht: {nachricht.strip()}", f"Zweck: {zweck.strip()}"]
+    if verlauf:
+        teile.append("Verlauf (neueste zuerst):")
+        for v in reversed(verlauf):
+            t = v["text"].strip()
+            if len(t) > MAX_VERLAUF_ZEICHEN:
+                t = t[:150] + " … " + t[-(MAX_VERLAUF_ZEICHEN - 150):]
+            teile.append(f"{v['rolle']}: {t}")
+    else:
+        teile.append("Verlauf: keiner")
+    return "\n".join(teile)
+
+
+class Intent(nn.Module):
+    """mmBERT-base, mean over the tokens, four linear heads."""
+
+    def __init__(self):
+        super().__init__()
+        self.encoder = AutoModel.from_pretrained(MODELL)
+        h = self.encoder.config.hidden_size
+        self.koepfe = nn.ModuleDict({"akt": nn.Linear(h, len(AKT)), "bezug": nn.Linear(h, len(BEZUG)),
+                                     "ja_nein": nn.Linear(h, len(JA_NEIN)), "sprache": nn.Linear(h, len(SPRACHEN))})
+        self.koepfe.load_state_dict(load_file(hf_hub_download(MODELL, "koepfe.safetensors")))
+
+    def forward(self, input_ids, attention_mask):
+        x = self.encoder(input_ids=input_ids, attention_mask=attention_mask).last_hidden_state
+        m = attention_mask.unsqueeze(-1).to(x.dtype)
+        v = (x * m).sum(1) / m.sum(1).clamp(min=1)
+        return {k: kopf(v) for k, kopf in self.koepfe.items()}
+
+
+tok = AutoTokenizer.from_pretrained(MODELL)
+modell = Intent().to(GERAET).eval()
+
+
+@torch.no_grad()
+def entscheide(faelle: list[dict], batch: int = 32) -> list[dict]:
+    """faelle: [{"zweck": str, "verlauf": [{"rolle": "nutzer"|"bot", "text": str}], "nachricht": str}]"""
+    aus = []
+    for i in range(0, len(faelle), batch):
+        teil = faelle[i:i + batch]
+        k = tok([eingabe(f["zweck"], f.get("verlauf", []), f["nachricht"]) for f in teil], truncation=True,
+                max_length=512, padding=True, return_tensors="pt").to(GERAET)
+        with torch.autocast(GERAET, dtype=torch.bfloat16, enabled=GERAET == "cuda"):
+            o = modell(k["input_ids"], k["attention_mask"])
+        akt, bez, spr = (o[n].float().softmax(-1).cpu() for n in ("akt", "bezug", "sprache"))
+        jn = o["ja_nein"].float().sigmoid().cpu().tolist()
+        for j in range(len(teil)):
+            p = dict(zip(JA_NEIN, jn[j]))
+            aus.append({
+                "akt": AKT[akt[j].argmax()], "bezug": BEZUG[bez[j].argmax()], "sprache": SPRACHEN[spr[j].argmax()],
+                "ja": [n for n in JA_NEIN if p[n] >= SCHWELLEN[n]],   # heads above their threshold
+                "werte": {n: round(x, 3) for n, x in p.items()},
+            })
+    return aus
+
+
+if __name__ == "__main__":
+    zweck = "Flight assistant on an airline website: helps passengers with questions about their flight."
+    verlauf = [{"rolle": "nutzer", "text": "Wie wird das Wetter heute in Wien bei der Landung?"},
+               {"rolle": "bot", "text": "In Wien sind es bei der Landung um 14:20 etwa 18 Grad, leicht bewölkt."}]
+    nachricht = sys.argv[1] if len(sys.argv) > 1 else "und morgen?"
+    print(json.dumps(entscheide([{"zweck": zweck, "verlauf": verlauf, "nachricht": nachricht}])[0],
+                     ensure_ascii=False, indent=1))

config.json

@@ -0,0 +1,78 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 1,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 1,
+  "global_attn_every_n_layers": 3,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "local_attention": 128,
+  "mask_token_id": 4,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 0,
+  "position_embedding_type": "sans_pos",
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 160000,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 160000,
+      "rope_type": "default"
+    }
+  },
+  "sep_token_id": 1,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.19.0",
+  "vocab_size": 256000
+}

intent.json

@@ -0,0 +1,68 @@
+{
+ "akt": [
+  "frage",
+  "auftrag",
+  "aussage",
+  "kurzantwort",
+  "korrektur",
+  "dank",
+  "gruss_smalltalk",
+  "beschwerde"
+ ],
+ "bezug": [
+  "neu",
+  "anschluss",
+  "themenwechsel"
+ ],
+ "ja_nein": [
+  "bedarf_aktuelle_daten",
+  "bedarf_nutzerdaten",
+  "bedarf_aktion",
+  "bedarf_dokumente",
+  "bedarf_rechnen",
+  "bedarf_allgemeinwissen",
+  "stimmung_besorgt",
+  "stimmung_veraergert",
+  "stimmung_dringend",
+  "rahmen",
+  "regelumgehung",
+  "unklar",
+  "unangemessen",
+  "krise",
+  "extremismus"
+ ],
+ "sprachen": [
+  "cs",
+  "de",
+  "en",
+  "es",
+  "fr",
+  "hr",
+  "hu",
+  "it",
+  "nl",
+  "pl",
+  "pt",
+  "ro",
+  "tr",
+  "uk",
+  "andere"
+ ],
+ "schwellen": {
+  "bedarf_aktuelle_daten": 0.4,
+  "bedarf_nutzerdaten": 0.4,
+  "bedarf_aktion": 0.5,
+  "bedarf_dokumente": 0.4,
+  "bedarf_rechnen": 0.6,
+  "bedarf_allgemeinwissen": 0.35,
+  "stimmung_besorgt": 0.5,
+  "stimmung_veraergert": 0.4,
+  "stimmung_dringend": 0.35,
+  "rahmen": 0.5,
+  "regelumgehung": 0.35,
+  "unklar": 0.35,
+  "unangemessen": 0.2,
+  "krise": 0.35,
+  "extremismus": 0.3
+ }
+}

koepfe.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5def0e4d53dad1991a00405163bf1eb7e1762d0be6e2848254f9c76a14734f18
+size 126708

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561cff0c735b8405d0225ca0212b80d24ec5dde264e0b9f607e43d8f3e4072a1
+size 1227771776

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17f7d8b9518c403d7429ad9eeeabb6eed49c8d3311de8ef4ed5ad811381a2ced
+size 34363441

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<bos>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<eos>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}