Quantized weights, tokenizer, temperatures, scripts

.gitattributes

@@ -33,3 +33,7 @@ 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
+jebadiah-27b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+jebadiah-27b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+jebadiah-27b-Q8_0.gguf 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 2026 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.

chat_template.jinja

@@ -0,0 +1,170 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + content + '<|im_end|>\n' }}
+        {%- elif reasoning_instructions %}
+            {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+        {%- endif %}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

jebadiah-27b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b4c7ab57ce90a57f9cafeb447cde0b68d2c68e874a065616319676d29ea672
+size 16810714560

jebadiah-27b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafef18a0757c05fceea401e3ae1e68996345fbfa2bc41310dd2b3187d118eb1
+size 19535701440

jebadiah-27b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b91f3142e982ffd7408fd4a2267f498a7ba5fe3d4206ad6382ad96385f911fe
+size 29047084480

scripts/ainode_prompt_verbatim.py

@@ -0,0 +1,294 @@
+"""AINode's prompt renderer, copied VERBATIM from the repo so training and serving render the
+same bytes. Do not edit by hand: regenerate with train/make_verbatim.py.
+
+source commit: e5c089386e0239c9eb270eeb490d181722b8da5b
+files: ainode/api/decide.py (SYSTEM_PROMPT, ANSWER_INSTRUCTION, MAX_OPTIONS, TOP_LOGPROBS, BOOLEAN_OPTIONS, DecideError, option_label, option_labels, serialize_state, build_messages)
+       ainode/api/systemone.py (CHOICE, NOUL, SCORE, QUESTION_TYPES, NOUL_OPTIONS, MIN_SCORE_LEVELS, MAX_SCORE_LEVELS, MAX_CRITERIA, Translated, option_text, criteria_pairs, choice_options, noul_options, score_options, translate_one, translate_questions)
+prompt_source_sha256: d2660ebec28bd3f1704235bda88d24a397c1c62475e740519cb8ef2d08f25fdd  (sha256 of the copied definitions, in this order)
+
+The served path is: systemone.translate_questions -> decide.normalize_questions (shape checks only)
+-> decide.build_messages(serialize_state(state), None, question, options) -> the model's chat
+template with add_generation_prompt=True and enable_thinking=False -> one label token.
+"""
+from __future__ import annotations
+
+import json
+from typing import Any, NamedTuple, Optional
+
+PROMPT_SOURCE_COMMIT = "e5c089386e0239c9eb270eeb490d181722b8da5b"
+PROMPT_SOURCE_SHA256 = "d2660ebec28bd3f1704235bda88d24a397c1c62475e740519cb8ef2d08f25fdd"
+
+SYSTEM_PROMPT = ("You are a decision function. Answer with the single letter "
+                 "of the best option and nothing else.")
+
+
+ANSWER_INSTRUCTION = "Answer with the label of one option and nothing else."
+
+
+MAX_OPTIONS = 255
+
+
+TOP_LOGPROBS = 20
+
+
+BOOLEAN_OPTIONS = ("yes", "no")
+
+
+class DecideError(Exception):
+    """A bad request shape. Carries the message the caller gets in the 4xx.
+
+    ``/v1/decide`` answers it as a 400 and ``/v1/systemone`` as the 422 the Jev
+    format specifies, so the message says what is wrong and never which status
+    somebody is about to put it in.
+    """
+
+
+def option_label(index: int) -> str:
+    """Zero-based option index to its letter label: A..Z, AA, AB, ... IU.
+
+    Bijective base-26 (spreadsheet columns), so the scheme keeps going past Z
+    without a separator and without ever colliding.
+    """
+    if index < 0:
+        raise ValueError("option index cannot be negative")
+    n = index + 1
+    out = ""
+    while n > 0:
+        n, rem = divmod(n - 1, 26)
+        out = chr(ord("A") + rem) + out
+    return out
+
+
+def option_labels(count: int) -> list[str]:
+    """The labels for a question with `count` options, in option order."""
+    return [option_label(i) for i in range(count)]
+
+
+def serialize_state(state: Any) -> str:
+    """The state as the model sees it: a string verbatim, anything else compact JSON."""
+    if state is None:
+        return ""
+    if isinstance(state, str):
+        return state
+    try:
+        return json.dumps(state, separators=(",", ":"), sort_keys=True,
+                          ensure_ascii=False)
+    except (TypeError, ValueError) as exc:
+        raise DecideError(f"'state' is not JSON-serializable: {exc}") from exc
+
+
+def build_messages(state: str, instructions: Optional[str], question: str,
+                   options: list[str]) -> list[dict]:
+    """The chat messages for one question. Pure, so the tests can pin the text.
+
+    The state comes BEFORE the question on purpose: every question in a request
+    then shares a byte-identical prefix (system message plus state), so the
+    engine's prefix cache prefills the shared part once no matter how many
+    questions are asked against it.
+    """
+    system = SYSTEM_PROMPT
+    extra = (instructions or "").strip()
+    if extra:
+        system = f"{SYSTEM_PROMPT}\n\n{extra}"
+    lines = ["STATE:", state, "", f"QUESTION: {question}", "", "OPTIONS:"]
+    lines += [f"{option_label(i)}. {opt}" for i, opt in enumerate(options)]
+    lines += ["", ANSWER_INSTRUCTION]
+    return [
+        {"role": "system", "content": system},
+        {"role": "user", "content": "\n".join(lines)},
+    ]
+
+
+CHOICE = "choice"
+
+
+NOUL = "noul"
+
+
+SCORE = "score"
+
+
+QUESTION_TYPES = (CHOICE, NOUL, SCORE)
+
+
+NOUL_OPTIONS = ("true", "false")
+
+
+MIN_SCORE_LEVELS = 2
+
+
+MAX_SCORE_LEVELS = 10
+
+
+MAX_CRITERIA = TOP_LOGPROBS
+
+
+class Translated(NamedTuple):
+    """One Jev question as the decision core sees it, plus the way back out.
+
+    ``options`` is what the model reads, one line per option. ``names`` is what
+    each of those options answers to on the wire, in the same order: a choice
+    criteria key verbatim, ``true`` / ``false``, or a score level's position.
+    Keeping the pair here is what lets the answer name the caller's own key
+    rather than the letter the engine was constrained to.
+    """
+
+    kind: str
+    question: str
+    options: list[str]
+    names: list[str]
+
+
+def option_text(name: str, description: Any) -> str:
+    """One option line: the name the answer will carry, then what it means.
+
+    The name comes first and VERBATIM because it is the string the caller's
+    client compares against, and a model that has read it beside its description
+    is choosing between meanings rather than between labels. The description is
+    flattened to one line, because the prompt renders one option per line and a
+    description with a newline in it would read as two options.
+    """
+    if isinstance(description, str) and description.strip():
+        return f"{name}: {' '.join(description.split())}"
+    return name
+
+
+def criteria_pairs(key: str, criteria: Any, kind: str) -> list[tuple[str, Any]]:
+    """The ``(name, description)`` pairs of an object ``criteria``, in order.
+
+    Insertion order is the rubric order for a score, and JSON parsing preserves
+    it, so nothing here sorts. A name is validated stripped and kept as written:
+    the answer has to carry the caller's own key back, byte for byte, because the
+    caller's code looks that key up.
+    """
+    if not isinstance(criteria, dict) or not criteria:
+        raise DecideError(
+            f"question '{key}': a {kind} question needs a non-empty 'criteria' "
+            "object of {name: description}")
+    pairs: list[tuple[str, Any]] = []
+    for name, description in criteria.items():
+        if not isinstance(name, str) or not name.strip():
+            raise DecideError(f"question '{key}': every 'criteria' name must be a "
+                              f"non-empty string (got {name!r})")
+        if description is not None and not isinstance(description, str):
+            raise DecideError(f"question '{key}': the 'criteria' description for "
+                              f"'{name}' must be a string")
+        pairs.append((name.strip(), description))
+    return pairs
+
+
+def choice_options(key: str, criteria: Any) -> tuple[list[str], list[str]]:
+    """A choice question's options and the criteria keys they answer to."""
+    pairs = criteria_pairs(key, criteria, "choice")
+    if len(pairs) < 2:
+        raise DecideError(f"question '{key}': a choice needs at least 2 'criteria' "
+                          f"options, got {len(pairs)}")
+    if len(pairs) > MAX_CRITERIA:
+        raise DecideError(
+            f"question '{key}': {len(pairs)} 'criteria' options is more than the "
+            f"{MAX_CRITERIA} this node can report a probability for. One engine "
+            f"call carries back the top {TOP_LOGPROBS} labels, so a wider option "
+            "set would answer with a distribution missing its tail")
+    return ([option_text(name, desc) for name, desc in pairs],
+            [name for name, _ in pairs])
+
+
+def noul_options(key: str, criteria: Any) -> tuple[list[str], list[str]]:
+    """A noul's two options, always ``true`` then ``false``.
+
+    The criteria block is optional here, and may describe one side only: some
+    clients send both, some send neither, and a yes-or-no question is still
+    answerable from its instructions alone. What a caller may not do is rename
+    the sides, because the answer is P(true) and nothing else can stand in for
+    it.
+    """
+    described: dict[str, Any] = {}
+    if criteria is not None:
+        if not isinstance(criteria, dict):
+            raise DecideError(f"question '{key}': 'criteria' must be an object of "
+                              "{true: description, false: description}")
+        for name, description in criteria.items():
+            flat = name.strip() if isinstance(name, str) else name
+            if flat not in NOUL_OPTIONS:
+                raise DecideError(f"question '{key}': a noul's 'criteria' names only "
+                                  f"'true' and 'false' (got {name!r})")
+            if description is not None and not isinstance(description, str):
+                raise DecideError(f"question '{key}': the 'criteria' description for "
+                                  f"'{flat}' must be a string")
+            described[flat] = description
+    return ([option_text(name, described.get(name)) for name in NOUL_OPTIONS],
+            list(NOUL_OPTIONS))
+
+
+def score_options(key: str, criteria: Any) -> tuple[list[str], list[str]]:
+    """A score's levels in rubric order: a list by position, an object by insertion.
+
+    Both spellings are accepted because both are in the wild: the list form names
+    the levels and nothing else, the object form names them and says what each
+    one means. Either way position 0 is the first level the caller wrote, which
+    is what the legend and the expected score are counted against.
+    """
+    if isinstance(criteria, list):
+        names: list[str] = []
+        for level in criteria:
+            if not isinstance(level, str) or not level.strip():
+                raise DecideError(f"question '{key}': every 'criteria' level must be "
+                                  f"a non-empty string (got {level!r})")
+            names.append(level.strip())
+        options = list(names)
+    elif isinstance(criteria, dict):
+        pairs = criteria_pairs(key, criteria, "score")
+        names = [name for name, _ in pairs]
+        options = [option_text(name, desc) for name, desc in pairs]
+    else:
+        raise DecideError(
+            f"question '{key}': a score question needs 'criteria', either an ordered "
+            "list of levels or an object of {level: description}")
+    if not MIN_SCORE_LEVELS <= len(names) <= MAX_SCORE_LEVELS:
+        raise DecideError(
+            f"question '{key}': a score's 'criteria' needs {MIN_SCORE_LEVELS} to "
+            f"{MAX_SCORE_LEVELS} ordered levels, got {len(names)}")
+    if len(set(names)) != len(names):
+        raise DecideError(f"question '{key}': 'criteria' repeats a level name. Every "
+                          "level must be distinct so a score names one of them")
+    return options, names
+
+
+def translate_one(key: str, spec: Any) -> Translated:
+    """One question off the wire. Reads three fields and ignores the rest.
+
+    ``type``, ``instructions`` and ``criteria`` are the whole question as far as
+    this route is concerned, which is also exactly what JDE's
+    ``questionsForWire`` sends. A field beyond them belongs to the caller's own
+    code, so it is neither read nor echoed.
+    """
+    if not isinstance(spec, dict):
+        raise DecideError(f"question '{key}' must be an object")
+    kind = spec.get("type")
+    if kind not in QUESTION_TYPES:
+        raise DecideError(f"question '{key}': 'type' must be one of "
+                          f"{', '.join(QUESTION_TYPES)} (got {kind!r})")
+    instructions = spec.get("instructions")
+    if not isinstance(instructions, str) or not instructions.strip():
+        raise DecideError(f"question '{key}' needs a non-empty 'instructions' string")
+    criteria = spec.get("criteria")
+    if kind == NOUL:
+        options, names = noul_options(key, criteria)
+    elif kind == SCORE:
+        options, names = score_options(key, criteria)
+    else:
+        options, names = choice_options(key, criteria)
+    return Translated(kind, instructions.strip(), options, names)
+
+
+def translate_questions(raw: Any) -> dict[str, Translated]:
+    """Every question in the body, in the order the caller wrote them."""
+    if not isinstance(raw, dict) or not raw:
+        raise DecideError("'questions' must be a non-empty object of {id: question}")
+    out: dict[str, Translated] = {}
+    for key, spec in raw.items():
+        if not isinstance(key, str) or not key.strip():
+            raise DecideError("every question id must be a non-empty string")
+        out[key] = translate_one(key, spec)
+    return out
+

scripts/decide_gguf.py

@@ -0,0 +1,96 @@
+"""Run a Jebadiah GGUF through llama.cpp's llama-server and print typed answers.
+
+The prompt is rendered in Python exactly as AINode's /v1/systemone does (jebadiah_prompt.py, the chat
+template with thinking off) and the rendered text goes to llama-server's raw /completion endpoint, so the
+server's own chat template never touches it. Nothing is generated: the answer is read off the log
+probabilities of the single-token option labels ("A", "B", ...) at the answer position, renormalised over
+those labels, with the model's per-type temperature from temperatures.json applied.
+
+  llama-server -m jebadiah-27b-Q4_K_M.gguf -c 4096 -np 1 --port 8080
+  python scripts/decide_gguf.py --server http://127.0.0.1:8080 --request scripts/example-request.json
+
+--tokenizer is a folder (or Hub repo id) with tokenizer.json, tokenizer_config.json and chat_template.jinja;
+this repository ships them, so the default is the folder above scripts/. Needs `transformers` (the tokenizer
+only, no torch) and nothing else outside the standard library.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import math
+import os
+import sys
+import urllib.request
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, HERE)
+from jebadiah_prompt import Renderer, answer_from_probs  # noqa: E402
+
+
+def load_renderer(tokenizer: str, max_tokens: int = 2048) -> Renderer:
+    from transformers import AutoTokenizer
+    tok = AutoTokenizer.from_pretrained(tokenizer)
+    if tok.pad_token_id is None:
+        tok.pad_token = tok.eos_token
+    return Renderer(tok, max_tokens)
+
+
+def read_temperatures(path: str | None) -> dict:
+    if not path or not os.path.exists(path):
+        return {}
+    return {k: float(v) for k, v in json.load(open(path))["temperatures"].items()}
+
+
+def post(server: str, path: str, body: dict, timeout: float = 900) -> dict:
+    req = urllib.request.Request(server.rstrip("/") + path, data=json.dumps(body).encode(),
+                                 headers={"Content-Type": "application/json"})
+    with urllib.request.urlopen(req, timeout=timeout) as r:
+        return json.loads(r.read())
+
+
+def label_logprobs(server: str, prompt: str, cand_ids: list[int], n_probs: int = 1000) -> tuple[list[float], int]:
+    """Log probabilities (full-vocab softmax, before any sampling) of each candidate token at the position
+    right after `prompt`. A label outside the top n_probs gets the smallest returned value, an upper bound
+    that is already negligible after renormalisation. Returns (logprobs, number of labels not returned)."""
+    r = post(server, "/completion", {"prompt": prompt, "n_predict": 1, "n_probs": n_probs,
+                                     "post_sampling_probs": False, "cache_prompt": False,
+                                     "temperature": 0.0})
+    top = r["completion_probabilities"][0]["top_logprobs"]
+    lp = {t["id"]: t["logprob"] for t in top}
+    floor = min(lp.values())
+    return [lp.get(c, floor) for c in cand_ids], sum(1 for c in cand_ids if c not in lp)
+
+
+def option_probs(logprobs: list[float], temperature: float = 1.0) -> list[float]:
+    """Softmax over the labels only, after dividing by the temperature. log p = logit - logsumexp(all
+    logits), and the constant cancels in the softmax, so this equals softmax(logits[labels] / T)."""
+    z = [x / temperature for x in logprobs]
+    m = max(z)
+    e = [math.exp(x - m) for x in z]
+    s = sum(e)
+    return [x / s for x in e]
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--server", default="http://127.0.0.1:8080", help="a running llama-server with a Jebadiah GGUF")
+    ap.add_argument("--request", required=True, help="JSON file: {state, questions: {id: {type, instructions, criteria}}}")
+    ap.add_argument("--tokenizer", default=os.path.dirname(HERE), help="folder or Hub repo id with the tokenizer and chat template")
+    ap.add_argument("--temperatures", default=os.path.join(os.path.dirname(HERE), "temperatures.json"))
+    ap.add_argument("--no-temperatures", action="store_true", help="raw probabilities, as the served route returns today")
+    ap.add_argument("--n-probs", type=int, default=1000)
+    a = ap.parse_args()
+    req = json.load(open(a.request))
+    renderer = load_renderer(a.tokenizer)
+    temps = {} if a.no_temperatures else read_temperatures(a.temperatures)
+    out = {"temperatures_applied": temps, "answers": {}}
+    for qid, q in req["questions"].items():
+        rd = renderer.render(req["state"], q)
+        lps, _ = label_logprobs(a.server, rd.prompt, rd.cand_ids, a.n_probs)
+        probs = option_probs(lps, float(temps.get(q["type"], 1.0)))
+        out["answers"][qid] = answer_from_probs(q, rd.keys, probs)
+    print(json.dumps(out, indent=1))
+
+
+if __name__ == "__main__":
+    main()

scripts/example-request.json

@@ -0,0 +1,4 @@
+{"state": {"ticket": "Customer says the invoice total does not match the quote."},
+ "questions": {
+  "route": {"type": "choice", "instructions": "Which team should take this ticket?", "criteria": {"billing": "an invoice, a charge or a refund", "support": "a product question", "sales": "a quote or a renewal"}},
+  "urgent": {"type": "noul", "instructions": "The customer is blocked from working.", "criteria": {"true": "work has stopped", "false": "it can wait"}}}}

scripts/jebadiah_prompt.py

@@ -0,0 +1,208 @@
+"""The Jebadiah prompt: AINode's own /v1/systemone -> /v1/decide rendering, then the base model's
+chat template, then ONE label token. Train, eval and the local server all go through here, and
+the served route (AINode) renders the same bytes because the renderer is AINode's, copied
+verbatim (ainode_prompt_verbatim.py, hashed into the training config).
+
+A question is the Jev wire shape {type, instructions, criteria}. AINode translates it to a list of
+option lines with letter labels (A..Z, AA..) and the wire names each label answers to:
+  choice -> the criteria keys, in criteria order (or the order the caller passes)
+  noul   -> ["true", "false"]  (always this order, AINode's rule)
+  score  -> the level texts in rubric order; we report them as level indices "0".."k-1"
+The answer position is the token right after the generation prompt, and the candidate tokens are
+the label strings themselves ("A", "B", ...), each one ordinary token at that boundary (checked
+against the tokenizer at load time).
+"""
+from __future__ import annotations
+
+import json
+from dataclasses import dataclass
+
+from ainode_prompt_verbatim import (
+    MAX_CRITERIA,
+    PROMPT_SOURCE_COMMIT,
+    PROMPT_SOURCE_SHA256,
+    Translated,
+    build_messages,
+    criteria_pairs,
+    option_label,
+    option_text,
+    serialize_state,
+    translate_one,
+)
+
+# Keys that must never appear inside a question object sent to the model. The linter rejects
+# them; the server refuses them.
+LABEL_KEYS = {"label", "labels", "expected", "passingAnswer", "passing_answer", "answer", "answers",
+              "target", "targets", "gold", "reference", "truth", "correct"}
+
+CHAT_TEMPLATE_KWARGS = {"add_generation_prompt": True, "enable_thinking": False, "thinking": False}
+
+
+def flatten_text(v) -> str:
+    """Instructions and descriptions must be strings on AINode's wire. Sources that ship an object
+    or a list (Kev's {question, focus}) are flattened once, at conversion time, by joining the
+    string values with a space. Never called on a state."""
+    if v is None:
+        return ""
+    if isinstance(v, str):
+        return v.strip()
+    if isinstance(v, dict):
+        return " ".join(s for s in (flatten_text(x) for x in v.values()) if s)
+    if isinstance(v, list):
+        return " ".join(s for s in (flatten_text(x) for x in v) if s)
+    return json.dumps(v, ensure_ascii=False)
+
+
+def wire_keys(q: dict, order: list | None = None) -> list[str]:
+    """The answer keys of a question in the order the options are shown."""
+    t = q["type"]
+    crit = q.get("criteria")
+    if t == "choice":
+        keys = list(crit) if isinstance(crit, dict) else [str(c) for c in crit]
+        if order is not None:
+            assert sorted(order) == sorted(keys), "order must be a permutation of the option keys"
+            keys = list(order)
+        return keys
+    if t == "noul":
+        return ["true", "false"]
+    if t == "score":
+        return [str(i) for i in range(len(crit))]
+    raise ValueError(f"unknown question type {t!r}")
+
+
+def reorder_choice(q: dict, order: list) -> dict:
+    """The same choice question with its criteria in `order` (AINode shows criteria order)."""
+    crit = q["criteria"]
+    if not isinstance(crit, dict):
+        crit = {str(c): None for c in crit}
+    return {**q, "criteria": {k: crit[k] for k in order}}
+
+
+@dataclass
+class Rendered:
+    prompt: str            # the chat-templated text ending in the generation prompt
+    keys: list[str]        # wire keys in display order
+    letters: list[str]     # the label shown for each key, same order
+    cand_ids: list[int]    # token id of each label at the answer boundary, same order
+    truncated: bool        # the state was cut to fit the token budget
+    label_scheme: str = "ainode"   # "ainode" (option_label, what /v1/decide emits) or "extended"
+
+
+class Renderer:
+    """Renders (state, question) exactly as AINode's /v1/systemone would, with this tokenizer's
+    chat template, and knows the label token ids."""
+
+    def __init__(self, tokenizer, max_tokens: int = 2048):
+        self.tok = tokenizer
+        self.max_tokens = max_tokens
+        self._label_ids: dict[str, int] = {}
+        # every label AINode can emit up to 255 options must be one ordinary token at the boundary
+        probe = self.render_messages("x", "q?", ["o1", "o2"])
+        base = tokenizer.encode(probe, add_special_tokens=False)
+        specials = set(tokenizer.all_special_ids)
+        for i in range(255):
+            lab = option_label(i)
+            comb = tokenizer.encode(probe + lab, add_special_tokens=False)
+            suffix = comb[len(base):]
+            if comb[:len(base)] != base or len(suffix) != 1 or suffix[0] in specials:
+                break
+            self._label_ids[lab] = suffix[0]
+        self.max_options = len(self._label_ids)
+        if self.max_options < 26:
+            raise ValueError(f"only {self.max_options} labels are single tokens in this tokenizer")
+        # Past AINode's single-token range (68 labels on the Qwen3.5 tokenizer: A..Z, AA..AZ,
+        # BA..BP) the served route cannot answer anyway (its cap is 20). For the LOCAL read of a
+        # wider question (Jevals Banking77, 77 options) we fall back to an extended alphabet: the
+        # same A..Z, then every two-letter uppercase string that is one ordinary token at the
+        # boundary, in alphabetical order. Rendered.label_scheme says which alphabet was used.
+        import string
+        self._extended: list[tuple[str, int]] = [(L, i) for L, i in self._label_ids.items() if len(L) == 1]
+        for a in string.ascii_uppercase:
+            for b in string.ascii_uppercase:
+                lab = a + b
+                comb = tokenizer.encode(probe + lab, add_special_tokens=False)
+                suffix = comb[len(base):]
+                if comb[:len(base)] == base and len(suffix) == 1 and suffix[0] not in specials:
+                    self._extended.append((lab, suffix[0]))
+        self.max_options_extended = len(self._extended)
+
+    def render_messages(self, state_text: str, question: str, options: list[str],
+                        letters: list[str] | None = None) -> str:
+        messages = build_messages(state_text, None, question, options)
+        if letters is not None:
+            # the extended alphabet: swap AINode's letters for ours in the option lines, nothing else
+            user = messages[1]["content"]
+            head, _, rest = user.partition("\nOPTIONS:\n")
+            lines = rest.split("\n")
+            for i in range(len(options)):
+                assert lines[i].startswith(f"{option_label(i)}. ")
+                lines[i] = f"{letters[i]}. " + lines[i][len(option_label(i)) + 2:]
+            messages[1]["content"] = head + "\nOPTIONS:\n" + "\n".join(lines)
+        return self.tok.apply_chat_template(messages, tokenize=False, **CHAT_TEMPLATE_KWARGS)
+
+    def render(self, state, q: dict, order: list | None = None) -> Rendered:
+        if q["type"] == "choice" and order is not None:
+            q = reorder_choice(q, order)
+        crit = q.get("criteria")
+        if q["type"] == "choice" and isinstance(crit, dict) and len(crit) > MAX_CRITERIA:
+            # AINode's route refuses this many options (its top-20 logprob read); the local read
+            # renders them the same way and scores every label directly off the logits
+            pairs = criteria_pairs("q", crit, "choice")
+            t = Translated("choice", str(q.get("instructions", "")).strip(),
+                           [option_text(n, d) for n, d in pairs], [n for n, _ in pairs])
+        else:
+            t = translate_one("q", q)
+        keys = wire_keys(q, order)
+        n_opt = len(t.names)
+        scheme = "ainode"
+        if n_opt <= self.max_options:
+            letters = [option_label(i) for i in range(n_opt)]
+            cand_ids = [self._label_ids[L] for L in letters]
+            shown = None
+        elif n_opt <= self.max_options_extended:
+            letters = [L for L, _ in self._extended[:n_opt]]
+            cand_ids = [i for _, i in self._extended[:n_opt]]
+            shown = letters
+            scheme = "extended"
+        else:
+            raise ValueError(f"{n_opt} options exceed the {self.max_options_extended} single-token labels")
+        state_text = serialize_state(state)
+        prompt = self.render_messages(state_text, t.question, t.options, shown)
+        truncated = False
+        n = len(self.tok.encode(prompt, add_special_tokens=False))
+        if n > self.max_tokens:
+            # cut the state from its end so the question, options and template survive intact
+            overhead = n - len(self.tok.encode(state_text, add_special_tokens=False))
+            keep = max(self.max_tokens - overhead - 4, 16)
+            ids = self.tok.encode(state_text, add_special_tokens=False)[:keep]
+            state_text = self.tok.decode(ids) + " [truncated]"
+            prompt = self.render_messages(state_text, t.question, t.options, shown)
+            truncated = True
+        return Rendered(prompt, keys, letters, cand_ids, truncated, scheme)
+
+
+def answer_from_probs(q: dict, keys: list[str], probs: list[float]) -> dict:
+    """The Jev wire answer for one question from its probabilities over `keys` (display order).
+    choice: {type, choice, confidence, probabilities}; noul: {type, noul}; score: {type, score,
+    confidence, legend, probabilities}. Ties: choice -> the option listed first; score -> the
+    lower level (the Jevals rule). Confidence is (p_max - 1/n) / (1 - 1/n), the chance-corrected
+    top probability AINode's route also reports."""
+    t = q["type"]
+    if t == "noul":
+        return {"type": "noul", "noul": round(float(probs[keys.index("true")]), 6)}
+    best = 0
+    for i, p in enumerate(probs):
+        if p > probs[best]:
+            best = i
+    n = len(keys)
+    p_max = float(probs[best])
+    confidence = 1.0 if n == 1 else (p_max - 1.0 / n) / (1.0 - 1.0 / n)
+    if t == "choice":
+        return {"type": "choice", "choice": keys[best], "confidence": round(confidence, 6),
+                "probabilities": {k: round(float(p), 6) for k, p in zip(keys, probs)}}
+    expected = sum(int(k) * float(p) for k, p in zip(keys, probs))
+    crit = q.get("criteria") or []
+    legend = {str(i): (c if isinstance(c, str) else str(c)) for i, c in enumerate(crit)} if isinstance(crit, list) \
+        else {str(i): k for i, k in enumerate(crit)}
+    return {"type": "score", "score": round(expected, 6), "confidence": round(confidence, 6),
+            "legend": legend, "probabilities": {k: round(float(p), 6) for k, p in zip(keys, probs)}}

temperatures.json

@@ -0,0 +1,77 @@
+{
+ "temperatures": {
+  "choice": 1.2321,
+  "noul": 1.297,
+  "score": 1.1423
+ },
+ "applied_target": "train",
+ "calib_file": "/workspace/jeb/data-v1/calib.jsonl",
+ "n": {
+  "choice": 225,
+  "noul": 147,
+  "score": 549
+ },
+ "fits": {
+  "hard": {
+   "choice": {
+    "T": 0.8349,
+    "nll_before": 0.3342,
+    "nll_after": 0.33
+   },
+   "noul": {
+    "T": 0.9013,
+    "nll_before": 0.3097,
+    "nll_after": 0.3086
+   },
+   "score": {
+    "T": 0.7558,
+    "nll_before": 0.883,
+    "nll_after": 0.8662
+   }
+  },
+  "train": {
+   "choice": {
+    "T": 1.2321,
+    "nll_before": 0.4621,
+    "nll_after": 0.4537
+   },
+   "noul": {
+    "T": 1.297,
+    "nll_before": 0.3953,
+    "nll_after": 0.387
+   },
+   "score": {
+    "T": 1.1423,
+    "nll_before": 1.059,
+    "nll_after": 1.055
+   }
+  }
+ },
+ "nll_before": {
+  "choice": 0.4621,
+  "noul": 0.3953,
+  "score": 1.059
+ },
+ "nll_after": {
+  "choice": 0.4537,
+  "noul": 0.387,
+  "score": 1.055
+ },
+ "ece_before": {
+  "choice": 0.1062,
+  "noul": 0.0737,
+  "score": 0.079
+ },
+ "ece_after": {
+  "choice": 0.12,
+  "noul": 0.0951,
+  "score": 0.1082
+ },
+ "accuracy": {
+  "choice": 0.9111,
+  "noul": 0.898,
+  "score": 0.6503
+ },
+ "score_targets": "ordinal",
+ "score_ordinal_adjacent": 0.2
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
+size 12809320

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "additional_special_tokens": [
+        "<|im_start|>",
+        "<|im_end|>",
+        "<|object_ref_start|>",
+        "<|object_ref_end|>",
+        "<|box_start|>",
+        "<|box_end|>",
+        "<|quad_start|>",
+        "<|quad_end|>",
+        "<|vision_start|>",
+        "<|vision_end|>",
+        "<|vision_pad|>",
+        "<|image_pad|>",
+        "<|video_pad|>"
+    ],
+    "bos_token": null,
+    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set reasoning_instructions = '' %}\n{%- if enable_thinking is undefined or enable_thinking is true %}\n    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}\n    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}\n        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}\n    {%- endif %}\n    {%- if resolved_reasoning_effort == 'xhigh' %}\n        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}\n    {%- elif resolved_reasoning_effort == 'low' %}\n        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}\n    {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if reasoning_instructions %}\n        {{- reasoning_instructions + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '<|im_start|>system\\n' + (reasoning_instructions + '\\n\\n' if reasoning_instructions else '')  + content + '<|im_end|>\\n' }}\n        {%- elif reasoning_instructions %}\n            {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- elif reasoning_instructions %}\n        {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined and tool_call.arguments != '' %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+    "extra_special_tokens": {
+        "audio_bos_token": "<|audio_start|>",
+        "audio_eos_token": "<|audio_end|>",
+        "audio_token": "<|audio_pad|>",
+        "image_token": "<|image_pad|>",
+        "video_token": "<|video_pad|>",
+        "vision_bos_token": "<|vision_start|>",
+        "vision_eos_token": "<|vision_end|>"
+    }
+}