Roka v0.2 initial release — decontaminated SFT, Apache 2.0

.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
+gguf/roka-v0.2-Q4_K_M.gguf 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 +1,243 @@
+---
+language:
+- tr
+- en
+license: apache-2.0
+library_name: transformers
+base_model: AlicanKiraz0/Kara-Kumru-v1.0-2B
+pipeline_tag: text-generation
+tags:
+- turkish
+- tool-calling
+- function-calling
+- hermes
+- kara-kumru
+- mistral
+- gguf
+---
+
+# Roka — Turkish Tool-Calling Fine-Tune of Kara-Kumru 2B
+
+Roka is a supervised fine-tune of `AlicanKiraz0/Kara-Kumru-v1.0-2B` that teaches a 2B-parameter Turkish language model to use five tools (web search, calculator, date/time, weather, URL reader) via a Hermes-style `<tool_call>…</tool_call>` output format.
+
+This is a **v0.2 research preview**, released for reproducibility and community feedback. It is not a production-grade tool-calling agent and has known weaknesses (see *Limitations*).
+
+The v0.2 training set is fully decontaminated against the evaluation set: no test-set query appears verbatim in train or validation.
+
+## Model at a glance
+
+| | |
+|---|---|
+| **Base model** | `AlicanKiraz0/Kara-Kumru-v1.0-2B` (Mistral architecture, Llama-3 chat template, Turkish-pretrained) |
+| **Upstream base** | `vngrs-ai/Kumru-2B` |
+| **Parameters** | ~2.15B |
+| **Fine-tuning** | Full fine-tuning, 3 epochs, LR 5e-5 linear, bf16, TRL SFTTrainer |
+| **Hardware** | Single NVIDIA A6000 (~65 min / epoch ~22 min) |
+| **Languages** | Primarily Turkish; ~13% of the training mix is English (Glaive-sourced synthetic tool-calling examples) |
+| **License** | Apache 2.0 (inherited from base chain) |
+
+## Tool set
+
+| Tool | Description |
+|---|---|
+| `web_search` | Internet search (DuckDuckGo) |
+| `calculator` | Arithmetic expression evaluator |
+| `datetime` | Date/time and calendar arithmetic (9 actions: `today`, `now`, `day_of_week`, `add_days`, `date_diff`, `days_until`, `day_of_year`, `end_of_month`, `days_until_weekday`) |
+| `hava_durumu` | Weather query by city name |
+| `sayfa_oku` | URL content reader |
+
+The model is trained to emit tool calls as:
+
+```
+<tool_call>
+{"name": "datetime", "arguments": {"action": "today"}}
+</tool_call>
+```
+
+Tool results are fed back to the model wrapped in `<tool_response>…</tool_response>` inside a user turn, and the model synthesizes a final Turkish answer.
+
+## Evaluation
+
+The test set contains 260 Turkish prompts spread over six categories (simple tool calls, fullflow multi-step, parallel, multiple tools, irrelevance, adversarial). Scoring uses an alignment-aware harness (`scripts/rescore_aligned.py`) that normalizes equivalent datetime actions and accepts semantically equivalent arithmetic expressions.
+
+### Overall results (Roka v0.2, April 2026)
+
+| View | n | Full-Match | Tool-Call Acc. | Name Acc. | Arg Acc. |
+|---|---|---|---|---|---|
+| **All test (held-out)** | 260 | **73.5%** | 93.1% | 71.9% | 60.6% |
+
+Every test query was verified to be absent from both `data/train.jsonl` and `data/val.jsonl`, so the 73.5% number above is a genuinely held-out measurement. See *Decontamination history* below for why this is lower than an earlier, un-decontaminated run.
+
+### Per-subcategory results
+
+| Subcategory | n | Full-Match |
+|---|---|---|
+| simple/web_search | 30 | **93.3%** |
+| simple/weather | 20 | **100.0%** |
+| simple/url_reader | 15 | **100.0%** |
+| simple/calculator | 20 | 70.0% |
+| simple/datetime | 15 | 46.7% |
+| fullflow | 35 | **80.0%** |
+| multiple | 45 | 64.4% |
+| parallel | 15 | **0.0%** |
+| adversarial/turkish_special | 10 | 90.0% |
+| adversarial/edge_case | 5 | 40.0% |
+| adversarial/ambiguous | 15 | 26.7% |
+| irrelevance/greeting | 15 | **100.0%** |
+| irrelevance/identity | 10 | **100.0%** |
+| irrelevance/opinion | 10 | **100.0%** |
+
+**Parallel tool calls score 0% because the training mix does not contain parallel-call examples.** This is a known gap, not a reproducibility failure.
+
+### Decontamination history
+
+During preparation for this release we audited the training set and found that **44 of the 260 test queries appeared verbatim in train/val** (8 in simple/datetime, 6 in simple/web_search, 7 in multiple, and the rest in irrelevance/identity and irrelevance/greeting). We removed all 76 matching train examples and 6 matching val examples, and retrained on the clean split. That retraining is the model reported above.
+
+For transparency we also report the before-and-after numbers on the 216 test queries that were **not** affected by the decontamination (i.e., the genuinely held-out subset from the *pre-cleanup* model's perspective):
+
+| Model | Training data | Clean-216 FM |
+|---|---|---|
+| v0.1 pre-clean | original (with 76 overlaps) | 78.2% |
+| **v0.2** (released) | decontaminated | **73.6%** |
+
+The ~4.6-point drop is informative: it is *not* contamination-inflation. The removed training examples were pattern-providing (datetime variants, fullflow web-search turns, distractor augmentations of the same base queries), and losing them cost about 4.6 points of generalization even on held-out queries. The cost of honest decontamination was larger than the narrow definition of "memorization gain" would predict. We report the post-decontamination number because it is the only one that is defensible as a held-out measurement. A future v0.3 will attempt to recover the gap by adding clean synthetic replacements for the removed examples.
+
+## Development journey (brief)
+
+Arriving at the final model required an honest amount of dead-ends.
+
+1. **Baseline (Run 10)** — 62.7% aligned FM with an earlier pipeline, before any of the spec-005 data work.
+2. **Phase A v1–v4 collapse** — four consecutive training runs where loss converged to near-zero but test-set Full-Match stayed at 0/260. All of them passed `loss` sanity checks, so the failure was invisible from inside the run.
+3. **Root cause** — TRL issue [#3910](https://github.com/huggingface/trl/issues/3910): the `max_seq_length` argument was silently renamed to `max_length` (default 1024) in TRL 0.20+. Every assistant turn longer than 1024 tokens (≈75% of our fullflow examples) was being truncated before it contributed to the loss. The model trained to completion on fragments, not on full tool-calling traces. Fix: pass `max_length=4096` explicitly.
+4. **Data iterations**
+   - Removed the `unit` argument from all `hava_durumu` training examples (the test set does not supply it). `simple/weather` Full-Match rose from 10% to 100%.
+   - Added 45 supplementary `datetime` examples covering `day_of_year`, `end_of_month`, and `days_until_weekday` — test actions that were absent from the R10 training data.
+   - Those supplementary examples caused a regression on `day_of_week` queries ("23 Nisan hangi güne denk geliyor?" was mis-routed to `day_of_year`). A targeted set of 30 `day_of_week` contrast examples fixed it.
+5. **Final v0.1 model** — 4,778 training / 509 validation examples, 795 optimizer steps. Reported 76.9% all-test, 78.2% on the clean-216 subset.
+6. **v0.2 — decontamination** — 76 train and 6 val examples whose first user turn matched a test query were removed, producing a 4,702 / 503 split. Retraining on this split gave the 73.5% number now reported above. The 4.6-point drop on the clean-216 subset between v0.1 and v0.2 is the cost of honest decontamination — see *Decontamination history*.
+
+Total compute used across Phase A and v0.2: ~5 A6000-hours.
+
+## Limitations
+
+- **Multi-turn pattern lock-in.** The SFT mix contains very few multi-turn tool-calling sequences. If the user starts with a chit-chat turn ("selam"), the model tends to stay in plain-chat mode on subsequent turns and skip the tool call. The provided `scripts/serve_ui.py` works around this by feeding only the current user message (without prior turns) into the tool-decision loop.
+- **Parallel tool calls: 0%.** Not trained.
+- **`hava_durumu` has no temporal parameter.** Queries like "yarın İstanbul'da hava" still produce `{"city": "İstanbul"}` because that is what the schema allows. The fix is a schema change + data regeneration, not a prompt change.
+- **Adversarial/ambiguous: 40%.** The model is easily nudged off-task by ambiguous phrasing.
+- **Long-passage synthesis is brittle.** When `sayfa_oku` returns several paragraphs, the synthesized summary sometimes fragments quotes in an unnatural way.
+- **Hermes parser coupling.** Native OpenAI-style `tool_calls` parsing via `llama-server` requires the provided `training/roka_tool_template.jinja` chat template and requires the client to pass the full list of 5 tools. Passing a subset confuses llama.cpp's Hermes detector.
+- **Scoring discrepancy.** The in-training `training/eval.py` scorer disagrees slightly with the alignment-aware rescorer. Only the rescored numbers are reported above. Resolving the discrepancy is open work.
+
+## Training data
+
+- **4,778 train / 509 validation** examples, Hermes-format chat turns.
+- **~72% Turkish, ~13% English, ~15% short/symbolic.** The English fraction is Glaive-sourced synthetic tool-calling data retained for multi-tool pattern coverage.
+- **Deterministic generators** for `calculator`, `datetime`, `hava_durumu` (in `training/generators/`).
+- **Real DuckDuckGo search results** cached in `data/ddg_cache.json` and used to construct `web_search` fullflow examples.
+- **PII scan**: only two flagged matches in user-facing content, both false positives (embedded WSJ article IDs). No email addresses, Turkish ID numbers, credit cards, or IP addresses found.
+
+## Contamination verification
+
+The released v0.2 model is trained on a split where **no test query appears verbatim** in either train or validation. The decontamination script (`scripts/decontaminate.py`) normalizes whitespace and case before matching. The pre-decontamination overlap distribution (all removed in v0.2) was:
+
+| Subcategory | Overlap (removed) |
+|---|---|
+| irrelevance/identity | 8 / 10 |
+| irrelevance/greeting | 11 / 15 |
+| simple/datetime | 8 / 15 |
+| simple/web_search | 6 / 30 |
+| multiple | 7 / 45 |
+| adversarial/turkish_special | 1 / 10 |
+| adversarial/opinion | 1 / 10 |
+| simple/weather | 1 / 20 |
+| fullflow | 1 / 35 |
+
+Because augmentation variants of each base query (masked/distractor versions) shared the same user turn, removing 44 unique queries deleted 76 train examples and 6 val examples in total. The remaining 4,702 / 503 split is what v0.2 was trained on.
+
+This decontamination is **exact-string**, not fuzzy. Near-duplicates (paraphrases that return the same tool call) are still present. Closing the paraphrase loophole requires a more elaborate embedding-based deduplication pass, which is left for v0.3.
+
+## Repository layout
+
+```
+src/                    Inference clients (transformers & llama-server)
+training/
+  tools.py              Tool schemas + training system prompt
+  train.py              TRL SFTTrainer entry point
+  eval.py               Test-set scorer (in-training)
+  roka_tool_template.jinja   llama-server chat template with Hermes detection hook
+  generators/           Deterministic data generators per tool
+scripts/
+  work_pipeline.py      End-to-end pod orchestration
+  pod_run_and_dump.py   On-pod training → prediction dump → HF upload
+  rescore_aligned.py    Alignment-aware rescorer (authoritative numbers)
+  serve_ui.py           FastAPI chat UI wrapping the agent
+data/
+  train.jsonl, val.jsonl, test_set.json
+specs/005-post-run10-75/   Spec, plan, and task list for this iteration
+```
+
+## Reproducibility
+
+1. Clone the repo and install requirements:
+   ```bash
+   pip install -r requirements.txt
+   ```
+2. Regenerate the training set (deterministic):
+   ```bash
+   python -m training.build_dataset
+   ```
+3. Train (RunPod-hosted, ~1 GPU-hour on an A6000):
+   ```bash
+   python -m scripts.work_pipeline
+   ```
+4. Rescore predictions with the alignment-aware harness:
+   ```bash
+   python -m scripts.rescore_aligned --predictions .work/artifacts/predictions/<run_id>.json
+   ```
+
+The training recipe is fully specified in `training/config.yaml`. The only hyperparameter that is unusually specific is `max_length: 4096` in `training/train.py` — removing it reproduces the Phase A v1–v4 collapse described above.
+
+## Intended use and out-of-scope use
+
+**Intended**: Turkish-language tool-calling agents for well-defined tools, research on small-model function calling, educational demonstrations of the SFT pipeline.
+
+**Out of scope**:
+- Safety-critical applications. The model has not been evaluated for harmful-content refusal beyond what Kara-Kumru inherits from its base.
+- Parallel / agentic planning over large tool catalogs.
+- Multi-turn conversational agents that need to preserve long prior context.
+- Any application that requires the model to use tools not present in the training schema.
+
+## License
+
+This repository and the released weights are distributed under the **Apache License 2.0**, inherited from both `AlicanKiraz0/Kara-Kumru-v1.0-2B` and its upstream base `vngrs-ai/Kumru-2B`. See `LICENSE`.
+
+## Citation
+
+If you use Roka in research, please cite both the base model and this work:
+
+```bibtex
+@misc{roka_2026,
+  title  = {Roka: Turkish Tool-Calling Fine-Tune of Kara-Kumru 2B},
+  author = {Bilgin, Ersan},
+  year   = {2026},
+  url    = {https://huggingface.co/ersanbil/roka}
+}
+
+@misc{karakumru_2025,
+  title  = {Kara-Kumru-v1.0-2B},
+  author = {Kiraz, Alican},
+  year   = {2025},
+  url    = {https://huggingface.co/AlicanKiraz0/Kara-Kumru-v1.0-2B}
+}
+```
+
+## Acknowledgements
+
+- **vngrs-ai** for the open Turkish base model `Kumru-2B`.
+- **Alican Kiraz** for the Turkish-conversational fine-tune `Kara-Kumru-v1.0-2B`.
+- **Hugging Face TRL / Unsloth** for the training stack.
+- **Glaive-AI function-calling dataset** for the English portion of the multi-tool synthetic mix.
+
+## Contact and feedback
+
+Issues and pull requests are welcome on the GitHub mirror. This is a research preview — please file bugs for any behavior that contradicts the documented limitations above; those are the interesting cases.

chat_template.jinja

@@ -0,0 +1,5 @@
+{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 3,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 10752,
+  "max_position_embeddings": 8192,
+  "model_type": "mistral",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.4",
+  "use_cache": false,
+  "vocab_size": 50180
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    3
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.5.4"
+}

gguf/roka-v0.2-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e565e14a0cc4c5b0de9376fd7838143bdc09321e5cbf0845a6cf14c4790b7671
+size 1458575232

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf89c2de19eaef8351c7c9d34d6dc6d696fa2d79898d187420192d57cd7519c
+size 4750344848

roka_tool_template.jinja

@@ -0,0 +1,73 @@
+{#-
+  Roka tool-calling chat template — Llama-3 header format + Hermes-style <tool_call> parsing.
+
+  Compatible with llama.cpp's Hermes-2-Pro output parser (detected by the literal
+  "<tool_call>" string in this template source). Uses Kara-Kumru's Llama-3 special
+  tokens: <|start_header_id|>, <|end_header_id|>, <|eot_id|>.
+
+  Design notes:
+    - The model was fine-tuned with an exact Turkish system prompt from
+      `training/tools.py::get_system_prompt()`. That prompt already contains the
+      tool schemas and calling conventions. We therefore DO NOT synthesize a
+      generic Hermes-English tool block from `tools=[...]` — doing so made the
+      model go meta / mis-route, because it never saw that format in training.
+    - Callers should pass the training system prompt via `messages[0]` (role=system).
+      Any `tools=[...]` parameter is accepted but ignored when building the prompt;
+      its only job is to let llama.cpp expose the parsed result via OpenAI's
+      `tool_calls` field.
+    - The literal string "<tool_call>" below (inside a comment hint) is what
+      llama.cpp uses to detect Hermes-2-Pro output format: do not remove it.
+
+  Format hint for llama.cpp detector: the assistant wraps tool calls as
+  <tool_call>{"name": "...", "arguments": {...}}</tool_call>.
+-#}
+{%- macro llama3_header(role) -%}
+<|start_header_id|>{{ role }}<|end_header_id|>
+
+{% endmacro -%}
+
+{{- bos_token -}}
+
+{%- for message in messages -%}
+  {%- if message.role == 'system' -%}
+    {{- llama3_header('system') -}}
+    {{- message.content | trim -}}
+    <|eot_id|>
+  {%- elif message.role == 'user' -%}
+    {{- llama3_header('user') -}}
+    {{- message.content | trim -}}
+    <|eot_id|>
+  {%- elif message.role == 'assistant' -%}
+    {{- llama3_header('assistant') -}}
+    {%- if message.content -%}
+      {{- message.content | trim -}}
+    {%- endif -%}
+    {%- if message.tool_calls is defined and message.tool_calls -%}
+      {%- for tc in message.tool_calls -%}
+        {%- if tc.function is defined -%}
+          {%- set call = tc.function -%}
+        {%- else -%}
+          {%- set call = tc -%}
+        {%- endif %}
+<tool_call>
+{%- if call.arguments is string %}
+{"name": "{{ call.name }}", "arguments": {{ call.arguments }}}
+{%- else %}
+{{ {'name': call.name, 'arguments': call.arguments} | tojson }}
+{%- endif %}
+</tool_call>
+      {%- endfor -%}
+    {%- endif -%}
+    <|eot_id|>
+  {%- elif message.role == 'tool' -%}
+    {{- llama3_header('user') -}}
+<tool_response>
+{{ message.content }}
+</tool_response>
+    <|eot_id|>
+  {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+  {{- llama3_header('assistant') -}}
+{%- endif -%}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<BOS>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<EOS>",
+  "extra_special_tokens": [
+    "<tool_call>",
+    "</tool_call>",
+    "<tool_response>",
+    "</tool_response>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<UNK>"
+}