Release Macaron-V1.1

.eval_results/README.md

@@ -0,0 +1,11 @@
+# Evaluation Results
+
+These three results are registered against Hugging Face benchmark datasets and can link to their benchmark leaderboards. They do not include HF Jobs `verifyToken` values, so Hugging Face should display them as self-reported rather than verified results.
+
+| Benchmark | Dataset | Task ID | Macaron-V1.1 |
+|---|---|---|---:|
+| Toolathlon-Verified | [`hkust-nlp/Toolathlon`](https://huggingface.co/datasets/hkust-nlp/Toolathlon) | `toolathlon_verified` | 76.0 |
+| DeepSWE v1.1 | [`datacurve/deep-swe`](https://huggingface.co/datasets/datacurve/deep-swe) | `deep_swe` | 71.7 |
+| Terminal-Bench 3.0 | [`harborframework/terminal-bench`](https://huggingface.co/datasets/harborframework/terminal-bench) | `terminalbench_3` | 31.4 |
+
+ChatBench v2, AutomationBench, SWE-Marathon, and UI4ABench v2 remain model-card self-reported results because their corresponding HF benchmark registrations are not available for this release.

.eval_results/deep_swe_v1_1.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: datacurve/deep-swe
+    task_id: deep_swe
+  value: 71.7
+  source:
+    url: https://huggingface.co/mindlab-research/Macaron-V1.1
+    name: Macaron-V1.1 model card

.eval_results/terminalbench_3.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: harborframework/terminal-bench
+    task_id: terminalbench_3
+  value: 31.4
+  source:
+    url: https://huggingface.co/mindlab-research/Macaron-V1.1
+    name: Macaron-V1.1 model card

.eval_results/toolathlon_verified.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: hkust-nlp/Toolathlon
+    task_id: toolathlon_verified
+  value: 76.0
+  source:
+    url: https://huggingface.co/mindlab-research/Macaron-V1.1
+    name: Macaron-V1.1 model card

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/v1_1_benchmark.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,29 @@
+GLM-5.3 License
+
+Copyright (c) 2026 Z.AI
+
+Permission is hereby granted, free of charge, to any person or entity (the "Licensee") obtaining a copy of this software — including the model weights, parameters, configuration files, inference and training code, and associated documentation (collectively, the "Software") — to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software; to run, deploy, fine-tune, or otherwise modify the Software and create derivative works from it; and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+1. The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. The Licensee's use of the Software must comply with applicable laws and regulations.
+
+2. "Model as a Service" means giving a third party access to language model inference or fine-tuning (e.g., via API) in a manner that allows such third party to exercise meaningful control over the inputs, parameters, or training data. This does not include (a) end-user products with model capabilities solely embedded within specific features or harnesses, or (b) mere relaying of requests to models hosted by others.
+If the Licensee or any of its affiliates operates a Model as a Service business, and the aggregate revenue of the Licensee and its affiliates exceeds 10 billion US dollars (or the equivalent in other currencies) in total over any consecutive 12 months, the Licensee must pass Z.AI's security review before using the Software or its derivative works for any commercial purpose. The scope and method of the security review shall be reasonably determined by Z.AI.
+
+3. THE SOFTWARE AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL Z.AI OR ITS AFFILIATES OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+For any questions regarding this license, please contact glmlicense@z.ai.
+
+-----
+
+版权所有 (c) 2026 Z.AI
+
+特此免费授予任何获得本软件副本的个人或实体（"被许可方"）——包括模型权重、参数、配置文件、推理和训练代码及相关文档（统称"软件"）——不受限制地处理本软件的权利，包括但不限于：使用、复制、修改、合并、发布、分发、再许可和/或销售软件副本；运行、部署、微调或以其他方式修改软件并创建衍生作品；以及允许获得软件的其他人行使上述权利，但须遵守以下条件：
+
+1. 上述版权声明和本许可声明应包含在软件的所有副本或实质性部分中。被许可方对软件的使用必须符合适用法律法规。
+
+2. "模型即服务"指以允许第三方对输入、参数或训练数据行使实质性控制的方式，向第三方提供语言模型推理或微调服务（如通过API）。不包括：(a) 模型能力仅嵌入特定功能或框架中的终端用户产品，或(b) 单纯转发请求至他人托管的模型。
+若被许可方或其关联方运营"模型即服务"业务，且被许可方及关联方在任意连续12个月内累计总收入超过100亿美元（或等值其他货币），则被许可方在使用软件或其衍生作品进行任何商业用途之前，须通过Z.AI的安全审查。安全审查的范围和方式由Z.AI合理确定。
+
+3. 软件及其任何输出和结果均按"现状"提供，不附带任何形式的保证，无论是明示还是暗示，包括但不限于适销性、特定用途适用性和不侵权的保证。在任何情况下，Z.AI或其关联方或版权持有人均不对任何索赔、损害或其他责任承担责任，无论该责任是基于合同、侵权或其他方式，因软件或使用软件而产生或与之相关。
+
+如对本许可有任何疑问，请联系 glmlicense@z.ai。

README.md

@@ -0,0 +1,152 @@
+---
+pipeline_tag: text-generation
+license: mit
+tags:
+- macaron
+- macaron-v1.1
+- glm-5.3
+- mixture-of-lora
+- personal-agent
+- tool-use
+- coding-agent
+- generative-ui
+- ui4a
+- eval-results
+model-index:
+- name: Macaron-V1.1
+  results:
+  - task: {type: text-generation, name: Chat}
+    dataset: {type: ChatBench-v2, name: ChatBench v2}
+    metrics: [{type: score, name: Score, value: 66.7}]
+  - task: {type: text-generation, name: Agent}
+    dataset: {type: AutomationBench, name: AutomationBench}
+    metrics: [{type: score, name: Score, value: 53.7}]
+  - task: {type: text-generation, name: Coding}
+    dataset: {type: SWE-Marathon, name: SWE-Marathon}
+    metrics: [{type: pass_at_2, name: pass@2 (%), value: 50.0}]
+  - task: {type: text-generation, name: Generative UI}
+    dataset: {type: UI4ABench-v2, name: UI4ABench v2}
+    metrics: [{type: score, name: Score, value: 83.2}]
+---
+
+# Macaron-V1.1
+
+<div align="center">
+  <img src="assets/mindlab_logo.svg" width="32%" alt="MindLab logo"/>
+</div>
+
+<p align="center">
+  🚀 <b>Hosted API:</b> <a href="https://mint.macaron.im/">Mint Recursive (International)</a> · <a href="https://mintcn.macaron.xin/">Mint Recursive (Mainland China)</a>
+  <br>
+  🧩 <b>Artifacts:</b> <a href="https://github.com/MindLab-Research/macaron-artifacts">Macaron Artifacts</a>
+  <br>
+  🛠️ <b>Serving project:</b> <a href="https://github.com/MindLab-Research/Mixture-of-LoRA-Harness">Mixture of LoRA (MoL) serving harness</a>
+  <br>
+  ✉️ <b>Correspondence:</b> contact@mindlab.ltd
+</p>
+
+Macaron-V1.1 is a **752B-parameter agent model** from MindLab Research, post-trained on **GLM-5.3**. It combines a **744B base model** with **four 2B LoRA specialists** for Chat, Agent, Coding, and Generative UI.
+
+Built with **Mint Recursive**, Mind Lab's serverless training and inference platform, Macaron-V1.1 follows Macaron-V1, which was based on GLM-5.2. The iteration from V1 to V1.1 was completed in two weeks, using a shared workflow for data preparation, experiments, checkpoint evaluation, and deployment.
+
+## Highlights
+
+- **752B release scale:** a 744B GLM-5.3 base with four release-labeled 2B LoRA specialists.
+- **Long-horizon coding:** SWE trajectories are organized into reproduction, localization, editing, verification, and recovery to reduce low-relevance exploration. Reported scores are 71.7 on DeepSWE v1.1 and 50.0 on SWE-Marathon.
+- **Complex office workflows:** training emphasizes selecting appropriate tools and avoiding unnecessary actions across documents, messages, and business systems, within the user's intent and authorization. AutomationBench reaches 53.7.
+- **Chat and Generative UI:** expanded real-world scenarios in ChatBench v2 and UI4ABench v2, with reported scores of 66.7 and 83.2 respectively.
+- **First-attempt UI delivery:** 58/60 tasks (96.67%), compared with GLM-5.3's 43/60 (71.67%), a 25-percentage-point increase.
+
+## Model Overview
+
+| Field | Value |
+|---|---|
+| Model name | Macaron-V1.1 |
+| Organization | MindLab Research |
+| Base model | GLM-5.3 |
+| Architecture | GLM-5.3 base + Mixture of LoRA (MoL) specialists |
+| Parameter footprint | 752B release label: 744B base + four 2B LoRA specialists |
+| Specialists | Chat, Agent, Coding, Generative UI |
+| Post-training platform | Mint Recursive |
+| Primary domains | Chat, personal-agent and office workflows, coding, Generative UI |
+| License | MIT |
+
+## Mixture of LoRA (MoL) Architecture
+
+| Specialist | Release-labeled size | Focus |
+|---|---|---|
+| Chat | 2B | Task progress and interaction quality in open-ended conversations |
+| Agent | 2B | Tool selection and execution in complex workflows |
+| Coding | 2B | Long-horizon software engineering and terminal tasks |
+| Generative UI | 2B | UI delivery, functionality, and visual design |
+
+The specialists share a 744B GLM-5.3 base.
+
+## Evaluation
+
+![Macaron-V1.1 benchmark results and evaluation notes](assets/v1_1_benchmark.png)
+
+| Category | Benchmark | Macaron V1.1 | Macaron V1 | GLM 5.3 | DeepSeek V4 Pro 0813 | Qwen 3.8 Max | Kimi K3 | Claude Opus 5 |
+|---|---|---:|---:|---:|---:|---:|---:|---:|
+| Chat | ChatBench v2 | **66.7** | 63.6 | 65.8 | 65.7 | 62.2 | 57.7 | 66.2 |
+| Agent | AutomationBench | **53.7** | 31.8 | 48.2* | 43.2* | 39.8* | 46.7* | 50.3* |
+| Agent | Toolathlon-Verified | 76.0 | 63.0 | 73.0* | 74.1* | 72.5* | 73.2* | **80.6*** |
+| Coding | DeepSWE v1.1 | **71.7** | 58.4 | 66.9* | 62.7* | 57.0* | 69.0* | 68.8* |
+| Coding | SWE-Marathon | **50.0** | 15.0 | 42.5* | 10.6* | — | 48.1* | **50.0*** |
+| Coding | Terminal-Bench 3.0 | 31.4 | 5.7 | 28.7 | 11.8* | 29.0* | 17.7* | **42.7*** |
+| GenUI | UI4ABench v2 | **83.2** | 75.8 | 77.6 | 77.7 | 79.3 | 80.6 | 81.4 |
+
+Higher is better. Bold marks the highest displayed score per row; `*` marks an externally sourced benchmark result; `—` means unavailable. The table reproduces the announcement chart, including its V1 comparison column. External results retain their original protocols and may differ in harness, task subset, execution budget, and aggregation. The table does not establish a controlled overall model ranking.
+
+Macaron-V1.1 exceeds or matches the displayed Opus 5 scores on ChatBench v2, AutomationBench, DeepSWE v1.1, SWE-Marathon, and UI4ABench v2. It scores below Opus 5 on Toolathlon-Verified and Terminal-Bench 3.0. These comparisons retain the protocol qualifications above.
+
+### Evaluation Protocols
+
+| Benchmark | Reported setup and metric |
+|---|---|
+| ChatBench v2 | Three independent runs per model–case pair using the production system prompt, user persona, and relevant conversation history. A privately deployed GLM-5.2 judge rates responses on a 1–5 scale; ratings are averaged over runs and cases and multiplied by 20. |
+| AutomationBench | Public 600-task split of v1.0.6 across six business domains, using the API toolset with at most 50 model-response steps per task. |
+| Toolathlon-Verified | Official Toolathlon evaluation service; pass@1. |
+| DeepSWE v1.1 | Claude Code agent harness; pass@3, with a task solved if any of up to three attempts succeeds. External official leaderboard results use mini-swe-agent. |
+| SWE-Marathon | pass@2. External leaderboard scores retain their respective published settings. |
+| Terminal-Bench 3.0 | Claude Code v2.1.207; pass@3. Client-reported output limit of 32,000 tokens per response. Agent timeouts are 10× each task's configured timeout, corresponding to 5–80 hours. |
+| UI4ABench v2 | 60 real-world-inspired UI-generation tasks of varying difficulty. Delivery measures first-attempt success; functional completeness is assessed through execution tests and visual quality through rendered screenshots. |
+
+The announcement chart identifies these external sources: [DeepSWE](https://deepswe.datacurve.ai/), [SWE-Marathon](https://www.swe-marathon.org/), [Toolathlon results](https://llm-stats.com/benchmarks/toolathlon), the Claude Opus 5 System Card for its Toolathlon score, [BenchLM](https://benchlm.ai/benchmarks/terminal-bench-3) for its Terminal-Bench score, and the [DeepSeek blog](https://www.deepseek.com/en/news/deepseek-v4-1-flash/) for Kimi K3 and DeepSeek V4 Pro Terminal-Bench scores. These are source attributions from the supplied chart, not independently revalidated leaderboard snapshots.
+
+The Toolathlon-Verified, DeepSWE v1.1, and Terminal-Bench 3.0 results are also registered in [`.eval_results/`](.eval_results/) against Hugging Face benchmark datasets, so Hugging Face can link them to their benchmark leaderboards. These files do not include HF Jobs `verifyToken` values; they should therefore be displayed as self-reported rather than verified results. ChatBench v2, AutomationBench, SWE-Marathon, and UI4ABench v2 remain model-card self-reported results because their corresponding HF benchmark registrations are not available for this release.
+
+**Reproducibility details pending:** checkpoint and adapter revisions, task-set revisions where unspecified, evaluation dates, complete generation settings, raw traces, confidence intervals, and train/evaluation overlap analysis. The ChatBench judge belongs to the same GLM family as the base model; cross-family judge calibration is not provided in the announcement.
+
+## Training with Mint Recursive
+
+Macaron-V1.1 was trained with Mint Recursive, Mind Lab's serverless model-training platform. The workflow integrates data preparation, experimentation, checkpoint evaluation, and deployment, enabling the iteration from Macaron-V1 to V1.1 to be completed in two weeks.
+
+Training focused on four capability areas:
+
+- **Coding:** Structuring long-horizon software-engineering trajectories around reproduction, localization, editing, verification, and recovery.
+- **Agent:** Improving tool selection and execution across documents, messaging, and business workflows.
+- **Chat:** Balancing task completion with interaction quality, emotional awareness, and resistance to sycophancy.
+- **Generative UI:** Improving first-attempt delivery, functional completeness, information hierarchy, and visual quality.
+
+## Usage
+
+### Hosted API
+
+- International users: [Mint Recursive](https://mint.macaron.im/).
+- Mainland China users: [Mint Recursive China](https://mintcn.macaron.xin/).
+
+Consult the platform documentation for available model IDs, authentication, pricing, and rate limits.
+
+### Open Weights and Self-Hosted Serving
+
+This repository includes the base checkpoint at the repository root and four LoRA specialists under `loras/L0` through `loras/L3`. Each LoRA directory contains `adapter_config.json` and `adapter_model.safetensors`, following the Macaron-V1-Venti release layout.
+
+## License
+
+This repository is released under the MIT License. Users should also respect any requirements inherited from the GLM-5.3 base model and from dependencies used by the serving harness.
+
+## Contact
+
+- Organization: MindLab Research
+- Correspondence: contact@mindlab.ltd

chat_template.jinja

@@ -0,0 +1,251 @@
+[gMASK]<sop>
+{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}
+{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
+{%- set clear_thinking = clear_thinking if clear_thinking is defined else false -%}
+{%- if tools -%}
+{%- macro tool_to_json(tool) -%}
+    {%- set ns_tool = namespace(first=true) -%}
+    {{ '{' -}}
+    {%- for k, v in tool.items() -%}
+        {%- if k != 'defer_loading' and k != 'strict' -%}
+            {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
+            {%- set ns_tool.first = false -%}
+            "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- endmacro -%}
+{%- macro tool_references_to_response(refs) -%}
+    {{- '<tool_response><tools>\n' -}}
+    {%- for tr in refs -%}
+        {%- for tool in tools -%}
+            {%- if 'function' in tool -%}
+                {%- set tool = tool['function'] -%}
+            {%- endif -%}
+            {%- if tool.name == tr.name -%}
+                {{- tool_to_json(tool) + '\n' -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endfor -%}
+    {{- '</tools></tool_response>' -}}
+{%- endmacro -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{%- if 'function' in tool -%}
+    {%- set tool = tool['function'] -%}
+{%- endif -%}
+{% if tool.defer_loading is not defined or not tool.defer_loading %}
+{{ tool_to_json(tool) }}
+{% endif %}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}
+                {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}
+                {{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro tool_response(text) -%}
+{{- '<tool_response>' + text + '</tool_response>' -}}
+{%- endmacro -%}
+{%- macro render_tool_response(m) -%}
+{%- if m.content is string -%}
+    {{- tool_response(m.content) -}}
+{%- elif m.content and m.content is not mapping and m.content.0.type == "tool_reference" -%}
+    {{- tool_references_to_response(m.content) -}}
+{%- elif is_list_of_outputs(m) -%}
+    {%- for tr in m.content -%}
+        {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == "tool_reference" -%}
+            {{- tool_references_to_response(tr.output) -}}
+        {%- else -%}
+            {{- tool_response(visible_text(tr.output)) -}}
+        {%- endif -%}
+    {%- endfor -%}
+{%- else -%}
+    {{- tool_response(visible_text(m.content)) -}}
+{%- endif -%}
+{%- endmacro -%}
+{%- macro id_of(obj) -%}
+    {%- if obj.tool_call_id -%}
+        {{- obj.tool_call_id -}}
+    {%- elif obj.id -%}
+        {{- obj.id -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro is_list_of_outputs(m) -%}
+    {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}
+{%- endmacro -%}
+{%- macro has_dup_tool_result_id(lo, hi, target) -%}
+    {%- set ns_cnt = namespace(n=0) -%}
+    {%- for k in range(lo, hi + 1) -%}
+        {%- set m = messages[k] -%}
+        {%- if is_list_of_outputs(m) -%}
+            {%- for entry in m.content -%}
+                {%- if id_of(entry) == target -%}
+                    {%- set ns_cnt.n = ns_cnt.n + 1 -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- elif id_of(m) == target -%}
+            {%- set ns_cnt.n = ns_cnt.n + 1 -%}
+        {%- endif -%}
+        {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}
+    {%- endfor -%}
+    {%- if ns_cnt.n > 1 -%}1{%- endif -%}
+{%- endmacro -%}
+{%- macro tc_id_exists(tcs, target) -%}
+    {%- set ns_f = namespace(found=false) -%}
+    {%- for tc in tcs -%}
+        {%- if id_of(tc) == target -%}
+            {%- set ns_f.found = true -%}
+            {%- break -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- if ns_f.found -%}1{%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) -%}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{%- for m in messages -%}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- elif '</think>' in content %}
+    {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
+    {%- set content = content.split('</think>')[-1] %}
+{%- endif %}
+{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
+{{ '<think>' + reasoning_content +  '</think>'}}
+{%- else -%}
+{{ '<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' -}}
+    {%- set block_start = loop.index0 -%}
+    {%- set ns_blk = namespace(end=block_start) -%}
+    {%- for j in range(block_start, messages|length) -%}
+        {%- if messages[j].role == 'tool' -%}
+            {%- set ns_blk.end = j -%}
+        {%- else -%}
+            {%- break -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns_a = namespace(tool_calls=none) -%}
+    {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}
+        {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}
+    {%- endif -%}
+    {%- set ns_chk = namespace(can_sort=true) -%}
+    {%- if not ns_a.tool_calls -%}
+        {%- set ns_chk.can_sort = false -%}
+    {%- else -%}
+        {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {%- set m = messages[k] -%}
+            {%- if is_list_of_outputs(m) -%}
+                {%- for entry in m.content -%}
+                    {%- set eid = id_of(entry) -%}
+                    {%- if not eid -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {%- set tk_id = id_of(m) -%}
+                {%- if not tk_id -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- for i in range(ns_a.tool_calls | length) -%}
+            {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}
+            {%- if not tc_id -%}
+                {%- set ns_chk.can_sort = false -%}
+            {%- endif -%}
+            {%- for j in range(i + 1, ns_a.tool_calls | length) -%}
+                {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- if ns_chk.can_sort -%}
+        {%- for tc in ns_a.tool_calls -%}
+            {%- set tc_id = id_of(tc) -%}
+            {%- for k in range(block_start, ns_blk.end + 1) -%}
+                {%- set m = messages[k] -%}
+                {%- if is_list_of_outputs(m) -%}
+                    {%- for entry in m.content -%}
+                        {%- set eid = id_of(entry) -%}
+                        {%- if eid == tc_id -%}
+                            {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == "tool_reference" -%}
+                                {{- tool_references_to_response(entry.output) -}}
+                            {%- else -%}
+                                {{- tool_response(visible_text(entry.output)) -}}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                {%- else -%}
+                    {%- set tk_id = id_of(m) -%}
+                    {%- if tk_id == tc_id -%}
+                        {{- render_tool_response(m) -}}
+                    {%- endif -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endfor -%}
+    {%- else -%}
+        {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {{- render_tool_response(messages[k]) -}}
+        {%- endfor -%}
+    {%- endif -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,224 @@
+{
+  "architectures": [
+    "GlmMoeDsaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "head_dim": 192,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "index_head_dim": 128,
+  "index_n_heads": 32,
+  "index_share_for_mtp_iteration": true,
+  "index_skip_topk_offset": 3,
+  "index_topk": 2048,
+  "index_topk_freq": 4,
+  "index_topk_pattern": null,
+  "indexer_rope_interleave": true,
+  "indexer_types": [
+    "full",
+    "full",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared"
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 1048576,
+  "mlp_layer_types": [
+    "dense",
+    "dense",
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "glm_moe_dsa",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "moe_router_dtype": "float32",
+  "n_group": 1,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 78,
+  "num_key_value_heads": 64,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 154820,
+  "pretraining_tp": 1,
+  "q_lora_rank": 2048,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "rope_theta": 8000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.15.0",
+  "use_cache": true,
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.12.0"
+}

loras/L0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98a8da364e6e51782ea6ad788ec7622f85b0b779db0df850889f02c52f9bc258
+size 15274464624

loras/L1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fc4c386e532bcff124274ae82200a3ac6e0ab5fbf66573cb021c90c2ced1aa
+size 15274464624

loras/L2/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4154c24c7b2161ef872a489b693e5d7e790fb3fe873a0ad340ca3e8594d587
+size 15274464624

loras/L3/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2ef17c3c41b4d14ebe1ca966a0d1bf17b5a2ef6f31a700ade3dd93f183e8bb
+size 15274464624

model-00001-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea8514ba4203b895c1cf3ee854f43aa001dfc2bfdcf1eca0639b3a9dbe7c899
+size 5342821416

model-00002-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0d35388e6bf76926c75301a9a108e9028090d8092c222ee7ab64d5180626fc
+size 5351970840

model-00003-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0648bb7f6790fee5c06a66b983ce74e6fc354aa4da4d057105f3dd4cdb1b824d
+size 5360347320

model-00004-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f657099dd323cc62d708a44945e1925dd71c5c95d5833b2a898acf4a1eb16db
+size 5360347208

model-00005-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659745f8c73ffaa06e83ec43ce6d158ce7f851c148ea069a28940e89f487a27c
+size 5359985352

model-00006-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a3ddd7737ed419653be0a605e562edab946e1dbd35f3c77efb1a65cd0c95f8
+size 5360347320

model-00007-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0143a46c4b9387b83b8aa8b6a92a7771b94de6835ae13672bb8fd0e5b1c91c
+size 5360347320

model-00008-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24e677a3d8ad0876c96324c6ec54220b307e0155283b33c3daba386343e0b11
+size 5360347144

model-00009-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d4a2079f92681ed094cb43d62752d2b5e911e8cb8b95b4b63e3c6e1247b5a3
+size 5366406944

model-00010-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36095a15bf9bf46579d7f77c26365fe3ee4494c1885d9293e18b6a3d72f515f
+size 5360347312

model-00011-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fae0083d38bcdd27043f32cd5f6736d70e8005536e2e3a628149c2c345a78e
+size 5360347288

model-00012-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5485f5cad7715f1c72b38aa2db88814b5ffbe393b13d68eb270ca4687d2f8912
+size 5363507640

model-00013-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474004a2b0676f24f835919349bd95d71e464963ac2c4d92361e839b5f3a10da
+size 5363246488

model-00014-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a50ce7752f50bed5f353ead62a795b7d5e2c0c2b90d6b2cfcb9da90330dbd8
+size 5360347312

model-00015-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc92c998cb160dad5e5d04983a53ae5bd74ba1d6fd6c64eaecf2a5ea48250b9d
+size 5360347224

model-00016-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4987d1ea2bebf85ff4797776f34382ab8039e6288b83357b562670a7b7c116d1
+size 5366406864

model-00017-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20d88d507bd2b34ef215e2933315f6e09ceaf313a0370ba751c37a51001ab2b
+size 5360347320

model-00018-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18862ef27b3e7634f9b4ac31810c108b65d0c6dcb30f7fb3a9181267cc850551
+size 5360347312

model-00019-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474598813f431faa5624fe6e7198486cb9c716e39a3d74677b00b496c178db10
+size 5360347152

model-00020-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb3e107eef5a0a9f030a0d0b6621c11400844b914f56d699c9047e03376233b
+size 5359985408

model-00021-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc715d9c0fc70125d5e5f2fb43d83b9036bc0b816da3bce85f9a59a28ac883c
+size 5360347320

model-00022-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a521e9b412045b462f32cd7951b2af2dc850e53636550154dbe568e83e6a4710
+size 5360347288

model-00023-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc8e7e81e5088eba510877a380067cb80dfa78b52aa1304051edff867715c5c
+size 5360347112

model-00024-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0137e62aac191292db1c6f3e80cd693fb7b714dc157646256147f0f0acd162af
+size 5366407008

model-00025-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b573908bb7c2ce35e74625da8a9bb2878d7bf7979daac945e964dc4130f6177
+size 5360347320

model-00026-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3846d304280f108c2e323fd1f28e3b7bc4fa7feed7e05babf96eb7fbe1e79265
+size 5360347232

model-00027-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58d62e4c5b32d965014643a161293410bed2b08c8190eb734ab36feb0f978d2
+size 5366406856

model-00028-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15338ddb3150ebb926372730385efa1946fce0590ff15eef0eef8989e7a98197
+size 5360347320

model-00029-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0e585673b76af97de9e6f5aa5757066162e1b5220e96879d0a4f322af381cf
+size 5360347320

model-00030-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1462a974258bcdf011c99d03f459f0cab5cf954d4571a2c4c0ce22e36159236
+size 5360347160