Add files using upload-large-folder tool

LICENSE-APACHE

@@ -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 +1,154 @@
+{%- 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 %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# 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 %}
+        {{- '<|im_start|>system\n' + content + '<|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 %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if 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 %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- 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 %}

config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "Qwen3_5MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "experts_implementation": "grouped_mm",
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "mamba_ssm_dtype": "float32",
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_5_moe_text",
+  "moe_intermediate_size": 512,
+  "mtp_num_hidden_layers": 1,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 16,
+  "num_experts": 256,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      11,
+      11,
+      10
+    ],
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 512,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.15.1",
+  "use_cache": false,
+  "vocab_size": 248320
+}

decider/prompt.py

@@ -0,0 +1,157 @@
+"""Prompt construction.  One context, N typed questions, N answer slots.
+
+All N decisions are read from a single forward pass: the logits at each
+"Answer k: (" slot are restricted to the option-letter tokens.  No answer
+letters are ever inserted, so slot k sees the context and all questions but
+no earlier answers (the decisions are conditionally independent given input).
+"""
+import random
+
+LETTERS = "ABCDEFGHIJ"
+NARROW = len(LETTERS)      # <= NARROW options: the original "(A) .. (J)" rendering, tokenized as a string (unchanged since v1)
+MAX_OPTIONS = 255          # width of the label head. > NARROW options: "wide" rendering, one label token per option:
+                           # A..Z then the first 229 two-letter upper-case strings that are single tokens (AA, AB, ...)
+ABSTAIN_PREFIXES = ("none of the above", "none of these", "not listed", "no suitable", "does not apply", "cannot tell")
+ABSTAIN_EXACT = ("other", "unsure", "something else", "neither of these", "other / not covered")
+
+
+def is_abstain_option(o):
+    o = o.strip().lower()
+    return o.startswith(ABSTAIN_PREFIXES) or o in ABSTAIN_EXACT
+
+
+_LABELS = {}
+_OPT_CACHE = {}
+
+
+def _enc_opt(tok, text):
+    """Token ids of ") <option text>" (cached: fixed label sets repeat the same strings millions of times)."""
+    key = (id(tok), text)
+    v = _OPT_CACHE.get(key)
+    if v is None:
+        v = tok.encode(f") {text}", add_special_tokens=False)
+        if len(_OPT_CACHE) < 2_000_000:
+            _OPT_CACHE[key] = v
+    return v
+
+
+def label_table(tok):
+    """(label strings, label token ids), MAX_OPTIONS entries; the first NARROW are A..J so narrow questions are unchanged."""
+    key = id(tok)
+    if key not in _LABELS:
+        import string
+        U = string.ascii_uppercase
+        names = list(U) + [a + b for a in U for b in U]
+        out = []
+        for n in names:
+            t = tok.encode(n, add_special_tokens=False)
+            if len(t) == 1:
+                out.append((n, t[0]))
+            if len(out) == MAX_OPTIONS:
+                break
+        assert len(out) == MAX_OPTIONS and len({i for _, i in out}) == MAX_OPTIONS
+        _LABELS[key] = ([n for n, _ in out], [i for _, i in out],
+                        tok.encode("\n(", add_special_tokens=False))
+    return _LABELS[key]
+
+
+def _select(q, rng, max_options):
+    opts = list(range(len(q.options)))
+    if len(opts) > max_options:
+        # always keep the gold and any abstain-style option (its mere presence must not carry information)
+        forced = {q.gold} | {i for i, o in enumerate(q.options) if is_abstain_option(o)}
+        others = [i for i in opts if i not in forced]
+        opts = rng.sample(others, max_options - len(forced)) + list(forced)
+    rng.shuffle(opts)
+    return opts
+
+
+def _options_ids(tok, q, opts):
+    if len(opts) <= NARROW:
+        return tok.encode("".join(f"\n({LETTERS[j]}) {q.options[oi]}" for j, oi in enumerate(opts)), add_special_tokens=False)
+    _, lab_ids, open_ids = label_table(tok); out = []
+    for j, oi in enumerate(opts):
+        out += open_ids + [lab_ids[j]] + _enc_opt(tok, q.options[oi])
+    return out
+
+
+def build_schema_first(example, tok, rng=None, max_options=NARROW, max_ctx_tokens=1536):
+    """Schema-first layout: all question/option blocks, then the context, then one answer slot per question.
+
+        Question 1: ...\nOptions:\n(A) ...          <- prefix: depends only on the questions, so its cache (attention KV and
+        \n\nQuestion 2: ...                            delta-net states) is computed once per schema and reused for every state
+        \n\nContext:\n<state>\n\nAnswer 1: (\nAnswer 2: (
+
+    The three parts are tokenized separately, so `ids[:prefix_len]` is identical for every state."""
+    rng = rng or random
+    perms = [_select(q, rng, max_options) for q in example.qs]
+    pre = schema_prefix_ids(tok, example.qs, perms)
+    suf, slots = schema_suffix_ids(tok, example.context, len(example.qs), max_ctx_tokens)
+    return dict(ids=pre + suf, slots=[len(pre) + s for s in slots], golds=[p.index(q.gold) if q.gold in p else -1 for p, q in zip(perms, example.qs)],
+                nopts=[len(p) for p in perms], perms=perms, prefix_len=len(pre))
+
+
+def schema_prefix_ids(tok, qs, perms=None):
+    """Token ids of the question/option blocks (the cacheable part of the schema-first layout)."""
+    multi = len(qs) > 1; pre = []
+    for k, q in enumerate(qs):
+        opts = perms[k] if perms is not None else list(range(len(q.options)))
+        pre += tok.encode(f"{chr(10) * 2 if k else ''}Question{' ' + str(k + 1) if multi else ''}: {q.text}\nOptions:", add_special_tokens=False) + _options_ids(tok, q, opts)
+    return pre
+
+
+def schema_suffix_ids(tok, context, n_q, max_ctx_tokens=1536):
+    """Token ids after the schema prefix: the context and one answer slot per question. Returns (ids, slot positions in ids)."""
+    ids = tok.encode("\n\nContext:\n", add_special_tokens=False) + tok.encode(context, add_special_tokens=False)[:max_ctx_tokens]; slots = []
+    for k in range(n_q):
+        ids += tok.encode(f"{chr(10) * 2 if k == 0 else chr(10)}Answer{' ' + str(k + 1) if n_q > 1 else ''}: (", add_special_tokens=False); slots.append(len(ids) - 1)
+    return ids, slots
+
+
+def build(example, tok, rng=None, max_options=NARROW, max_ctx_tokens=1536, layout="state_first"):
+    """Returns dict(ids=list[int], slots=list[int], golds=list[int], nopts=list[int], perms=list[list[int]])."""
+    if layout == "schema_first":
+        return build_schema_first(example, tok, rng, max_options, max_ctx_tokens)
+    rng = rng or random
+    ctx_ids = tok.encode("Context:\n" + example.context, add_special_tokens=False)[:max_ctx_tokens]
+    ids = list(ctx_ids)
+    slots, golds, nopts, perms = [], [], [], []
+    multi = len(example.qs) > 1
+    for k, q in enumerate(example.qs):
+        opts = list(range(len(q.options)))
+        if len(opts) > max_options:
+            # always keep the gold and any abstain-style option (its mere presence must not carry information)
+            forced = {q.gold} | {i for i, o in enumerate(q.options) if is_abstain_option(o)}
+            others = [i for i in opts if i not in forced]
+            keep = rng.sample(others, max_options - len(forced)) + list(forced)
+            opts = keep
+        rng.shuffle(opts)
+        head = f"\n\nQuestion{' ' + str(k + 1) if multi else ''}: {q.text}\nOptions:"
+        tail = f"\nAnswer{' ' + str(k + 1) if multi else ''}: ("
+        if len(opts) <= NARROW:
+            lines = [head] + [f"\n({LETTERS[j]}) {q.options[oi]}" for j, oi in enumerate(opts)] + [tail]
+            piece = tok.encode("".join(lines), add_special_tokens=False)
+        else:                                   # wide: "\n(" + <label token> + ") text", built from ids so every label is one token
+            _, lab_ids, open_ids = label_table(tok)
+            piece = tok.encode(head, add_special_tokens=False)
+            for j, oi in enumerate(opts):
+                piece += open_ids + [lab_ids[j]] + _enc_opt(tok, q.options[oi])
+            piece += tok.encode(tail, add_special_tokens=False)
+        ids.extend(piece)
+        slots.append(len(ids) - 1)          # position of " (" token
+        golds.append(opts.index(q.gold) if q.gold in opts else -1)
+        nopts.append(len(opts))
+        perms.append(opts)
+    return dict(ids=ids, slots=slots, golds=golds, nopts=nopts, perms=perms)
+
+
+def letter_ids(tok):
+    ids = label_table(tok)[1]
+    for j, L in enumerate(LETTERS):
+        assert tok.encode(L, add_special_tokens=False) == [ids[j]], L
+    return ids
+
+
+def render(example, tok, **kw):
+    b = build(example, tok, **kw)
+    return tok.decode(b["ids"])

decider/systemone.py

@@ -0,0 +1,139 @@
+"""Jev-shaped requests on top of the decider prompt format (same wire format as TypeSafe's POST /v1/systemone).
+
+    state      str | dict | list            JSON state is serialised compactly; questions may name a part by path (`ticket.messages[0].text`)
+    questions  {id: {"type": "choice", "instructions": ..., "criteria": {name: description | {...} | [...] | None}}      up to 255 options
+                     {"type": "score",  "instructions": ..., "criteria": [level 0 description, level 1 description, ...]}  2..10 levels
+                     {"type": "noul",   "instructions": ..., "criteria": {"true": ..., "false": ...} (optional)}}
+    ids are never shown to the model.  `instructions` and every description may be a string or any JSON value.
+"""
+import json, math
+
+MAX_CHOICE, MAX_LEVELS = 255, 10
+
+
+def _txt(v):
+    return v if isinstance(v, str) else json.dumps(v, ensure_ascii=False)
+
+
+ANNOTATE_MIN = 8
+
+
+def annotate_indices(x, min_len=ANNOTATE_MIN):
+    """Write each element's position into long arrays ({"_index": i, ...}).  A path such as `records[47].text` otherwise makes
+    the model count 47 elements; with the index written down it is a lookup (json_k64 probe: 0.49 -> 0.57 accuracy)."""
+    if isinstance(x, list):
+        if len(x) >= min_len:
+            return [({"_index": i, **annotate_indices(v, min_len)} if isinstance(v, dict) else {"_index": i, "value": annotate_indices(v, min_len)}) for i, v in enumerate(x)]
+        return [annotate_indices(v, min_len) for v in x]
+    if isinstance(x, dict):
+        return {k: annotate_indices(v, min_len) for k, v in x.items()}
+    return x
+
+
+def render_state(state, index_arrays=True):
+    if isinstance(state, str):
+        return state
+    return json.dumps(annotate_indices(state) if index_arrays else state, ensure_ascii=False)
+
+
+def render_question(spec):
+    """-> dict(question=str, options=[str], type=..., names=[...])  (names: what the answer reports for each option)"""
+    t = spec.get("type", "choice"); ins = _txt(spec.get("instructions", spec.get("question", ""))); crit = spec.get("criteria", spec.get("options"))
+    if not ins:
+        raise ValueError("question without instructions")
+    if t == "choice":
+        if isinstance(crit, (list, tuple)):
+            crit = {str(c): None for c in crit}
+        if not isinstance(crit, dict) or not 2 <= len(crit) <= MAX_CHOICE:
+            raise ValueError(f"choice criteria: a map of 2..{MAX_CHOICE} options")
+        names = list(crit); opts = [n if crit[n] in (None, "") else f"{n}: {_txt(crit[n])}" for n in names]
+    elif t == "score":
+        if isinstance(crit, dict):                                   # legend form {"0": "...", "1": "..."}
+            crit = [crit[k] for k in sorted(crit, key=float)]
+        if not isinstance(crit, (list, tuple)) or not 2 <= len(crit) <= MAX_LEVELS:
+            raise ValueError(f"score criteria: an ordered list of 2..{MAX_LEVELS} level descriptions")
+        names = list(range(len(crit))); opts = [f"{i}: {_txt(c)}" for i, c in enumerate(crit)]
+    elif t in ("noul", "bool"):
+        names = [False, True]; c = crit or {}
+        f, tr = c.get("false", c.get(False)), c.get("true", c.get(True))
+        opts = ["no" if f in (None, "") else f"no: {_txt(f)}", "yes" if tr in (None, "") else f"yes: {_txt(tr)}"]
+    else:
+        raise ValueError(f"unknown question type {t!r}")
+    return dict(question=ins, options=opts, type="noul" if t == "bool" else t, names=names, legend=[_txt(c) for c in crit] if t == "score" else None,
+                isolated=bool(spec.get("isolated", True)))
+
+
+# ---- isolated levels: every Score level is judged in its own row, without its number or its neighbours
+ISOLATED = "{q}\nProposed answer: {level}\nDoes the proposed answer fit?"
+_NUM = None
+
+
+def strip_level_number(text):
+    """"2: somewhat" -> "somewhat" (dataset legends carry the number; an isolated level must not)."""
+    import re
+    return re.sub(r"^\s*-?\d+\s*:\s*", "", text)
+
+
+def isolated_rows(question, levels):
+    """-> one yes/no question per level: [(question text, ["no", "yes"])]."""
+    return [(ISOLATED.format(q=question, level=strip_level_number(l)), ["no", "yes"]) for l in levels]
+
+
+def combine_isolated(p_yes):
+    """Per-level P(fits), each computed without reference to any other level -> a distribution over levels.
+    Also returns the unnormalised mass: near 1 when exactly one level fits, low when none does, high when several do."""
+    tot = sum(p_yes) or 1e-9
+    return [x / tot for x in p_yes], tot
+
+
+def plan_rows(rqs, isolated=True):
+    """One scoring row per question; a Score question with isolated levels becomes one yes/no row per level.
+    -> (rows [{"question", "options"}], index [(id, "iso" | "list", first row, n rows)])"""
+    rows, index = [], []
+    for k, r in rqs.items():
+        if isolated and r["type"] == "score" and r.get("isolated", True):
+            rws = isolated_rows(r["question"], r["legend"]); index.append((k, "iso", len(rows), len(rws))); rows += [dict(question=t, options=o) for t, o in rws]
+        else:
+            index.append((k, "list", len(rows), 1)); rows.append(dict(question=r["question"], options=r["options"]))
+    return rows, index
+
+
+def assemble(rqs, index, probs):
+    """probs: one probability list per row (plan_rows order) -> {id: answer}."""
+    out = {}
+    for k, kind, s, n in index:
+        if kind == "iso":
+            fit = [float(probs[s + j][1]) for j in range(n)]; p, mass = combine_isolated(fit); a = format_answer(rqs[k], p)
+            a["level_fit"] = {str(j): round(x, 4) for j, x in enumerate(fit)}; a["fit_mass"] = round(mass, 4); out[k] = a
+        else:
+            out[k] = format_answer(rqs[k], probs[s])
+    return out
+
+
+def certainty(p):
+    """1 - normalised entropy: 1 when all mass is on one option, 0 when the distribution is flat."""
+    h = -sum(x * math.log(x) for x in p if x > 0)
+    return max(0.0, 1.0 - h / math.log(len(p))) if len(p) > 1 else 1.0
+
+
+def format_answer(rq, p, nd=4):
+    """rq: render_question output; p: probabilities in option order."""
+    p = [float(x) for x in p[:len(rq["options"])]]; s = sum(p) or 1.0; p = [x / s for x in p]
+    j = max(range(len(p)), key=p.__getitem__)
+    if rq["type"] == "noul":
+        return {"type": "noul", "noul": round(p[1], nd)}
+    if rq["type"] == "choice":
+        return {"type": "choice", "choice": rq["names"][j], "confidence": round(p[j], nd), "certainty": round(certainty(p), nd),
+                "probabilities": {n: round(x, nd) for n, x in zip(rq["names"], p)}}
+    return {"type": "score", "score": round(sum(i * x for i, x in enumerate(p)), 2), "confidence": round(p[j], nd), "certainty": round(certainty(p), nd),
+            "legend": {str(i): d for i, d in enumerate(rq["legend"])}, "probabilities": {str(i): round(x, nd) for i, x in enumerate(p)}}
+
+
+def unique_tokens(items):
+    """Input tokens of a request whose rows share a prefix (the state): the prefix counts once."""
+    ids = [it["ids"] for it in items]
+    if len(ids) < 2:
+        return sum(len(x) for x in ids)
+    lcp = 0; short = min(len(x) for x in ids)
+    while lcp < short and all(x[lcp] == ids[0][lcp] for x in ids): lcp += 1
+    return lcp + sum(len(x) - lcp for x in ids)

decider_config.json

@@ -0,0 +1,11 @@
+{
+  "version": "WebJev-35B-A3B",
+  "temperature": 1.0,
+  "temperature_fitted": false,
+  "neutralize_none": false,
+  "base": "Qwen/Qwen3.5-35B-A3B-Base",
+  "max_options": 255,
+  "max_state_tokens": 32768,
+  "schema_first": false,
+  "isolated_levels": true
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "transformers_version": "5.15.1",
+  "use_cache": true
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d470d2cf5b558e3116157e90c3219e6d3ad1ebbc45f88e4b67bd264d257b076
+size 4861004088

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61d11068c241dd5553d3f17249e9feb6a6efc650440290749927c0ce268cf19
+size 4506714376

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcf875cbc24a98a2d74d4f686d3b13351222bd28d9dfc817a6aba4fdba970f8
+size 4989093232

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1306b32d1a93b9068e82119e19e4d576ba9fdcd830e38a57ba1fc5f10109c51
+size 4574152520

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4043440af420eb553b8c54ab382c88405f5f75239f8f93332c59f93f5f3073b
+size 4976513672

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d05bf9b8323cba64824491b41a47dde3ef42c18870657f77f8465f699da8a0
+size 4990860936

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af530a9b0d3c543a7b73fd999fe29d69963f0993faa231a43ab6291062120f0
+size 4564708264

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e0ba236e0b8675eb63b041d45c943d2fac238454347427fc9655d4ca4cb7c6
+size 4506716424

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf346c8db3f2ff9421cac54ee752d21b3cab61a7413c9216f8743afc0b53f83a
+size 4506716432

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6993d147b17589d7379327c110d150d46263db16d7b993b2122c1bc165eca4
+size 4989095576

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb59ff800e599db84a63156de95f1fa6e63a1fdcf1a7b0c204eff2849195fe6
+size 4499363680

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065dc19d5d033935eb6273bb08c06732989e7c92cc247e566a89cce6b0107244
+size 4506716472

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7841bbabde6adb13bdbc0e79415cddafe19c79a9a041a80c24ab2fe028efa0
+size 4989095576

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f6cdeaf9eadabeff34c1eaa458bdef09047c311f655d9ae82f3c2f6e6cb48c
+size 4574154552

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75849c68223ba4e86e9b0e71d8722fa88b8a547436f312250031eb50c8cceb8f
+size 3290673624

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 262144,
+  "model_specific_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|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "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+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}