Initial upload

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 2024 Alibaba Cloud
+
+   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 +1,137 @@
+---
+license: apache-2.0
+language:
+- kk
+- ru
+- en
+tags:
+- qwen3
+- kazakh
+- dare-ties
+- merge
+- noesis
+- dhcf-fno
+- 600m
+base_model:
+- ekitil/ekitil-core-qwen3-600m-kkru-base-v1
+- ekitil/ekitil-qwen3-600m-kk
+- ekitil/ekitil-qwen3-600m-kkru
+quantized_by: AMAImedia
+pipeline_tag: text-generation
+---
+
+# NOESIS-Qwen3-0.6B-Darwin-Ekitil-Sozkz-KZ-BF16
+
+**DARE-TIES merge of three Kazakh/Russian Qwen3-600M models, producing a stronger KK/RU specialist.**
+
+Released as part of the **NOESIS Professional Multilingual Dubbing Automation Platform**
+(framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).
+
+- **Founder:** Ilia Bolotnikov
+- **Organization:** [AMAImedia.com](https://www.amaimedia.com)
+- **X (Twitter):** [@AMAImediacom](https://x.com/AMAImediacom)
+- **LinkedIn:** [Ilia Bolotnikov](https://www.linkedin.com/in/ilia-bolotnikov)
+- **Telegram:** [@djbionicl](https://t.me/djbionicl)
+- **NOESIS version:** v14.7
+- **Release date:** 2026-04
+
+---
+
+## Model summary
+
+| Property | Value |
+| --- | --- |
+| Architecture | `Qwen3ForCausalLM` |
+| Parameters | ~600M |
+| Hidden size | 1 280 |
+| Layers | 28 |
+| Vocab size | 64 000 (custom KK/RU tokenizer) |
+| Precision | BF16 |
+| Disk footprint | ~1.3 GB |
+| Merge method | DARE-TIES (RNG seed 1729) |
+| Primary language | Kazakh (KK) |
+| Secondary language | Russian (RU) |
+
+---
+
+## Source models
+
+| Model | Role | Weight | Density |
+| --- | --- | --- | --- |
+| `ekitil-core-qwen3-600m-kkru-base-v1` | Base (foundation) | — | — |
+| `ekitil-qwen3-600m-kk` (step 4500) | KK specialist | 0.45 | 0.53 |
+| `ekitil-qwen3-600m-kkru` (step 2000) | KK+RU generalist | 0.35 | 0.53 |
+
+The base model provides the foundation architecture. DARE randomly drops (1 − density) of each
+task vector's weights and rescales survivors, then TIES elects majority-sign directions before
+summing into the merged model.
+
+---
+
+## Why this merge
+
+Each source model captures a different aspect of Kazakh language:
+- **ekitil-core** — balanced KK+RU base
+- **ekitil-kk** — maximally Kazakh-specialized (4 500 training steps)
+- **ekitil-kkru** — bilingual KK+RU (2 000 training steps)
+
+DARE-TIES combines all three while suppressing conflicting parameter updates, producing better
+KK coverage than any single model alone.
+
+---
+
+## How to use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "amaimedia/NOESIS-Qwen3-0.6B-Darwin-Ekitil-Sozkz-KZ-BF16"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+messages = [{"role": "user", "content": "Сәлем! Қазақ тілінде сөйлесейік."}]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=256, do_sample=True, temperature=0.7)
+print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
+```
+
+> **Note:** `vocab_size=64000` — custom Kazakh tokenizer, not Qwen3 standard 151 936.
+> Not compatible with standard Qwen3 tokenizer pipelines.
+
+---
+
+## NOESIS context
+
+In NOESIS this model provides **Kazakh language domain boost** (KK×10 weight multiplier)
+for the DUB-LM and CHAT specialists during knowledge distillation.
+
+> ⚠️ **KD note:** `vocab_size=64000` is incompatible with NOESIS student vocab (151 936).
+> Soft label extraction requires a custom cross-vocab projection layer.
+
+---
+
+## Provenance
+
+A `merge_provenance.json` file ships alongside the model weights with the full merge trace:
+source models, weights, densities, DARE-TIES parameters, and RNG seed.
+
+---
+
+## Citation
+
+```bibtex
+@misc{noesis_darwin_kz,
+  title     = {NOESIS-Qwen3-0.6B-Darwin-Ekitil-Sozkz-KZ-BF16},
+  author    = {Bolotnikov, Ilia},
+  year      = {2026},
+  publisher = {AMAImedia},
+  url       = {https://amaimedia.com}
+}
+```

config.json

@@ -0,0 +1,64 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 4480,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 64000,
+  "_name_or_path": "amaimedia/NOESIS-Qwen3-0.6B-Darwin-Ekitil-Sozkz-KZ-BF16"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.5.0",
+  "use_cache": true
+}

merge_provenance.json

@@ -0,0 +1,19 @@
+{
+  "noesis_version": "v14.7",
+  "method": "DARE-TIES",
+  "seed": 1729,
+  "base": "B:\\Downloads\\Portable\\NOESIS-VC-ONE\\models\\llm\\sozkz\\ekitil-core-qwen3-600m-kkru-base-v1",
+  "models": [
+    {
+      "path": "B:\\Downloads\\Portable\\NOESIS-VC-ONE\\models\\llm\\sozkz\\ekitil-qwen3-600m-kk\\step_4500",
+      "weight": 0.45,
+      "density": 0.53
+    },
+    {
+      "path": "B:\\Downloads\\Portable\\NOESIS-VC-ONE\\models\\llm\\sozkz\\ekitil-qwen3-600m-kkru\\step_2000",
+      "weight": 0.35,
+      "density": 0.53
+    }
+  ],
+  "output": "B:\\Downloads\\Portable\\NOESIS-VC-ONE\\models\\llm\\NOESIS-Qwen3-0.6B-Darwin-Ekitil-Sozkz-KZ-BF16"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f60bdbfcc6ba457fb1a3a1374d88213315f75db26139fe31abbfe8a03b149a
+size 1347608416

tokenizer_config.json

@@ -0,0 +1,6 @@
+{
+  "backend": "tokenizers",
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "TokenizersBackend"
+}