commit cd82c37be3afffc90b04e2cdaccb216409d06271
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Fri Oct 2 07:09:18 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: adgomant/adele-judge-qwen3-14B-cre
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..dffe933
--- /dev/null
+++ b/.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
+adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..2cd3fc0
--- /dev/null
+++ b/README.md
@@ -0,0 +1,151 @@
+---
+library_name: transformers
+tags:
+- text-generation
+- peft
+- adele
+- judge
+base_model: Qwen/Qwen3-14B
+datasets:
+- CFI-Kinds-of-Intelligence/ADeLe_battery_v1dot0
+---
+
+# ADeLe Distilled Judge
+
+This repository contains an ADeLe-suite-specific distilled judge. It scores a model response against a question and reference answer with an ordinal score from 1 to 5, then derives binary correctness with the ADeLe threshold.
+
+The repository root contains a merged Transformers model for standard loading. The original LoRA adapter is also included under `adapter/` for provenance and reuse.
+
+## Intended Use
+
+Use this model to score ADeLe-style examples where a question, reference answer, and model response are available. It is intended for out-of-model evaluation within the ADeLe benchmark suite, not as a general-purpose evaluator.
+
+## Input Format
+
+The recommended helper accepts:
+
+- `question`
+- `reference_answer` or `ground_truth`
+- `model_response`
+
+## Score Rubric
+
+Allowed scores: 1, 2, 3, 4, 5
+
+- 1: surely incorrect
+- 2: likely incorrect
+- 3: minimally correct or sufficient
+- 4: likely correct
+- 5: surely correct
+
+Binary label: scores greater than or equal to 3 are `CORRECT`; lower scores are `INCORRECT`.
+
+## Training And Validation Data
+
+| Split | Examples | Models |
+| --- | --- | --- |
+| train | 239,420 | 16 |
+| validation | 45,738 | 3 |
+
+- `train` models: `DK-R1-Dist-Qwen-1.5B`, `DK-R1-Dist-Qwen-32B`, `DK-R1-Dist-Qwen-7B`, `gemini-2.5-flash`, `gemini-3.1-pro`, `gpt-35-turbo`, `gpt-5.2`, `gpt4o`, `llama3d1-405b`, `llama3d2-11b`, `llama3d2-1b`, `llama3d2-90b`, `llama4-17B-128E`, `o1-mini`, `o1_re=low`, `o3-mini`
+- `validation` models: `DK-R1-Dist-Qwen-14B`, `gemini-3-flash`, `llama3d2-3b`
+
+## Data Quality And Label Construction
+
+Training labels are distilled from two proprietary judge scores used by the ADeLe evaluation pipeline to derive the official correctness signal. The configured source columns are `score_gpt4o` and `score_sonnet`.
+
+- Ordinal target: `floor(mean(score_gpt4o, score_sonnet))`.
+- Binary target: `CORRECT` when the ordinal target is >= `3`.
+- Judge-agreement filter: keep examples with `abs(score_gpt4o - score_sonnet) <= 1`.
+- Response-length filter: keep responses with at most `4096` base-tokenizer tokens before prompt formatting.
+- Sequence-length filter: keep full chat-formatted examples within `max_seq_length=8192`.
+
+## Validation Results
+
+Source artifact: `validation_trainer_metrics.json`.
+
+| Metric | Value |
+| --- | --- |
+| Epoch | 1.0000 |
+| Binary accuracy | 0.9894 |
+| Binary macro F1 | 0.9880 |
+| Precision, CORRECT | 0.9932 |
+| Recall, CORRECT | 0.9909 |
+| Precision, INCORRECT | 0.9817 |
+| Recall, INCORRECT | 0.9863 |
+| False negative rate, CORRECT | 0.0091 |
+| False positive rate, CORRECT | 0.0137 |
+| Ordinal accuracy | 0.9639 |
+| Ordinal macro F1 | 0.7351 |
+| Mean confidence | 0.9604 |
+
+## Recommended Inference
+
+Do not use free-form generation as the primary prediction method. The recommended path scores the restricted continuations `"1"`, `"2"`, `"3"`, `"4"`, and `"5"`.
+
+```python
+from transformers import pipeline
+
+judge = pipeline(
+    "adele-judge",
+    model="adgomant/adele-judge-qwen3-14-cre",
+    trust_remote_code=True,
+    device_map="auto",
+)
+result = judge(
+    {"question": "...", "reference_answer": "...", "model_response": "..."}
+)
+print(result)
+
+results = judge([
+    {"question": "...", "reference_answer": "...", "model_response": "..."},
+    {"question": "...", "ground_truth": "...", "model_response": "..."},
+], batch_size=8)
+```
+
+The result has this shape:
+
+```python
+{
+    "score": 4,
+    "label": "CORRECT",
+    "probs": {"1": 0.01, "2": 0.02, "3": 0.08, "4": 0.70, "5": 0.19},
+    "logprobs": {"1": -5.0, "2": -4.2, "3": -2.9, "4": -0.8, "5": -2.1},
+    "confidence": 0.70,
+    "margin": 1.3,
+    "entropy": 0.82,
+}
+```
+
+## Standard Transformers Loading
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("adgomant/adele-judge-qwen3-14-cre", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("adgomant/adele-judge-qwen3-14-cre", trust_remote_code=True)
+```
+
+`generation_config.json` uses safe one-token defaults for debugging, but `generate()` is not the recommended scoring method.
+
+## Metadata
+
+Training, filtering, split, tokenization, and metric artifacts available at packaging time are stored in `adele_judge_metadata.json`.
+
+The model is trained on distilled judge targets. These targets are useful for reproducing the ADeLe paper-style correctness signal at lower inference cost, but they should not be interpreted as independent human annotations.
+
+## References
+
+- ADeLe project page: [ADeLe v1.0](https://kinds-of-intelligence-cfi.github.io/ADELE/).
+- ADeLe paper and official correctness definition: [General scales unlock AI evaluation with explanatory and predictive power](https://www.nature.com/articles/s41586-026-10303-2).
+- Official ADeLe dataset: [CFI-Kinds-of-Intelligence/ADeLe_battery_v1dot0](https://huggingface.co/datasets/CFI-Kinds-of-Intelligence/ADeLe_battery_v1dot0).
+- Official instance-level model-response data used for distillation: [https://github.com/Kinds-of-Intelligence-CFI/ADeLe-AIEvaluation/tree/main/ADeLe_battery_data/subject_specific_instance_level_data](https://github.com/Kinds-of-Intelligence-CFI/ADeLe-AIEvaluation/tree/main/ADeLe_battery_data/subject_specific_instance_level_data).
+- Training and Hub packaging implementation: [https://github.com/adgomant/adele-judge](https://github.com/adgomant/adele-judge).
+
+## Limitations
+
+- ADeLe-specific judge; not a general-purpose evaluator.
+- Distilled from proprietary judge labels and inherits their noise, calibration, and biases.
+- Intended for scoring responses against a reference answer.
+- It should not produce explanations; the expected output is a single score.
+- Validation is out-of-model within the ADeLe suite, so transfer outside that suite should be measured before relying on it.
\ No newline at end of file
diff --git a/adapter/README.md b/adapter/README.md
new file mode 100644
index 0000000..7caaeb8
--- /dev/null
+++ b/adapter/README.md
@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1
\ No newline at end of file
diff --git a/adapter/adapter_config.json b/adapter/adapter_config.json
new file mode 100644
index 0000000..7776a73
--- /dev/null
+++ b/adapter/adapter_config.json
@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/adapter/adapter_model.safetensors b/adapter/adapter_model.safetensors
new file mode 100644
index 0000000..fbf80ce
--- /dev/null
+++ b/adapter/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ee829cf0d836f834e05f7fd8048ed8728a005134279148191bcc08ac9559bb
+size 513877864
diff --git a/adapter/chat_template.jinja b/adapter/chat_template.jinja
new file mode 100644
index 0000000..01be9b3
--- /dev/null
+++ b/adapter/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].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" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|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 %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- 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' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/adapter/tokenizer.json b/adapter/tokenizer.json
new file mode 100644
index 0000000..c7afbed
--- /dev/null
+++ b/adapter/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
diff --git a/adapter/tokenizer_config.json b/adapter/tokenizer_config.json
new file mode 100644
index 0000000..7d75d3b
--- /dev/null
+++ b/adapter/tokenizer_config.json
@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/adapter/training_args.bin b/adapter/training_args.bin
new file mode 100644
index 0000000..30c835c
--- /dev/null
+++ b/adapter/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b8e0e2fb5df1b2a243361e988314c091bebb39a1d6987c307d909b5412bd56
+size 5201
diff --git a/adele_judge_config.json b/adele_judge_config.json
new file mode 100644
index 0000000..0327618
--- /dev/null
+++ b/adele_judge_config.json
@@ -0,0 +1,28 @@
+{
+  "inference": {
+    "allowed_scores": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5"
+    ],
+    "binary_threshold": 3,
+    "method": "restricted_continuation_logprobs_fast"
+  },
+  "model": {
+    "base_model": "Qwen/Qwen3-14B",
+    "revision": null,
+    "thinking_mode": {
+      "apply_if_supported": true,
+      "enabled": false
+    }
+  },
+  "prompt": {
+    "system_prompt": "You are an answer quality evaluator. You will receive a question, a reference\nanswer, and a model response, each delimited by ### headers.\n\nRate the model response on the following scale:\n1 - Surely incorrect: the response is wrong or completely misses the point.\n2 - Likely incorrect: the response has significant errors or critical omissions.\n3 - Minimally correct / sufficient: the response is partially correct or borderline.\n4 - Likely correct: the response is mostly correct with minor issues.\n5 - Surely correct: the response is fully correct and complete.\n\nRules:\n- Base your rating strictly on correctness relative to the reference answer.\n- Ignore writing style, verbosity, or formatting unless they affect correctness.\n- If the final answer is correct but the reasoning contains substantive errors, lower the rating according to the severity of those errors.\n- Output only a single integer from 1 to 5. No explanation. No punctuation.\n"
+  },
+  "training": {
+    "max_seq_length": 4096,
+    "objective": "restricted_score_ce"
+  }
+}
\ No newline at end of file
diff --git a/adele_judge_metadata.json b/adele_judge_metadata.json
new file mode 100644
index 0000000..eb57d64
--- /dev/null
+++ b/adele_judge_metadata.json
@@ -0,0 +1,1059 @@
+{
+  "adapter_path": "runs/qwen3_14b_restricted_score_ce/adapter",
+  "allowed_scores": [
+    "1",
+    "2",
+    "3",
+    "4",
+    "5"
+  ],
+  "artifacts": {
+    "config.yaml": {
+      "data": {
+        "columns": {
+          "benchmark": "benchmark",
+          "example_id": "instance_id",
+          "judge_1_score": "score_gpt4o",
+          "judge_2_score": "score_sonnet",
+          "model_id": "model_id",
+          "question": "question",
+          "reference_answer": "ground_truth",
+          "response": "response",
+          "source": "source",
+          "task": "task"
+        },
+        "filters": {
+          "max_disagreement": 1,
+          "max_response_tokens": 4096,
+          "on_sequence_overflow": "skip"
+        },
+        "path": "data/processed/response_scores.parquet",
+        "prepared_dir": null,
+        "preprocessing_num_workers": 40,
+        "token_length_batch_size": 2048,
+        "tokenizers_parallelism": true
+      },
+      "distributed": {
+        "backend": "nccl",
+        "deepspeed": {
+          "config_overrides": {},
+          "gradient_clipping": "auto",
+          "offload_optimizer_device": "none",
+          "offload_param_device": "none",
+          "stage3_gather_16bit_weights_on_model_save": true,
+          "zero_stage": 2
+        },
+        "enabled": true,
+        "find_unused_parameters": false,
+        "fsdp": {
+          "activation_checkpointing": true,
+          "sharding_strategy": "full_shard",
+          "transformer_layer_cls_to_wrap": null,
+          "use_orig_params": true
+        },
+        "gradient_checkpointing": false,
+        "mixed_precision": "bf16",
+        "strategy": "ddp"
+      },
+      "evaluation": {
+        "length_buckets": [
+          0,
+          256,
+          512,
+          1024,
+          2048,
+          3072,
+          4096,
+          1000000000
+        ]
+      },
+      "hub": {
+        "commit_message": "Upload ADeLe distilled judge",
+        "create_pr": false,
+        "local_checkpoint_dir": null,
+        "max_shard_size": "5GB",
+        "output_staging_dir": null,
+        "private": false,
+        "repo_id": null
+      },
+      "inference": {
+        "allow_base_model": true,
+        "allowed_scores": [
+          "1",
+          "2",
+          "3",
+          "4",
+          "5"
+        ],
+        "batch_size": 64,
+        "binary_threshold": 3,
+        "generation_fallback": false,
+        "method": "restricted_continuation_logprobs_fast",
+        "require_adapter": false
+      },
+      "model": {
+        "adapter_path": null,
+        "attn_implementation": "sdpa",
+        "model_name_or_path": "Qwen/Qwen3-14B",
+        "revision": null,
+        "thinking_mode": {
+          "apply_if_supported": true,
+          "enabled": false
+        },
+        "trust_remote_code": true
+      },
+      "project": {
+        "output_dir": "runs/qwen3_14b_restricted_score_ce",
+        "run_name": "qwen3_14b_restricted_score_ce",
+        "seed": 42
+      },
+      "prompt": {
+        "system_prompt": "You are an answer quality evaluator. You will receive a question, a reference\nanswer, and a model response, each delimited by ### headers.\n\nRate the model response on the following scale:\n1 - Surely incorrect: the response is wrong or completely misses the point.\n2 - Likely incorrect: the response has significant errors or critical omissions.\n3 - Minimally correct / sufficient: the response is partially correct or borderline.\n4 - Likely correct: the response is mostly correct with minor issues.\n5 - Surely correct: the response is fully correct and complete.\n\nRules:\n- Base your rating strictly on correctness relative to the reference answer.\n- Ignore writing style, verbosity, or formatting unless they affect correctness.\n- If the final answer is correct but the reasoning contains substantive errors, lower the rating according to the severity of those errors.\n- Output only a single integer from 1 to 5. No explanation. No punctuation.\n"
+      },
+      "split": {
+        "held_out_model": null,
+        "lomo_validation_fraction": 0.05,
+        "lomo_validation_max_examples": 30000,
+        "lomo_validation_seed": 42,
+        "mode": "fixed_by_model",
+        "train_models": "auto_except_val_test",
+        "validation_models": [
+          "gemini-3-flash",
+          "DK-R1-Dist-Qwen-14B",
+          "llama3d2-3b"
+        ]
+      },
+      "training": {
+        "cache_tokenized_datasets": true,
+        "class_weighting": null,
+        "dtype": "bfloat16",
+        "eval_steps": 500,
+        "eval_subset_seed": 42,
+        "eval_subset_size": null,
+        "eval_subset_strategy": "stratified",
+        "eval_subset_stratify_columns": [
+          "model_id",
+          "target_score"
+        ],
+        "gradient_accumulation_steps": 4,
+        "learning_rate": 3e-05,
+        "length_column_name": "length",
+        "load_in_4bit": true,
+        "logging_steps": 10,
+        "lora_alpha": 64,
+        "lora_dropout": 0.0,
+        "lora_r": 32,
+        "loss": {
+          "class_weights": null,
+          "lambda_binary": 0.5,
+          "type": "ce_5way"
+        },
+        "lr_scheduler_type": "cosine",
+        "max_grad_norm": 1.0,
+        "max_seq_length": 4096,
+        "num_train_epochs": 1,
+        "objective": "restricted_score_ce",
+        "optim": "adamw_8bit",
+        "packing": false,
+        "per_device_eval_batch_size": 2,
+        "per_device_train_batch_size": 2,
+        "resume_from_checkpoint": null,
+        "save_steps": 500,
+        "save_total_limit": 10,
+        "score_class_weights": null,
+        "seed": 42,
+        "target_modules": "auto",
+        "train_sampling_strategy": "random",
+        "warmup_ratio": 0.03,
+        "weight_decay": 0.0
+      }
+    },
+    "dataset_filtering_report.json": {
+      "after_disagreement_filter": 287811,
+      "after_response_length_filter": 285310,
+      "effective_prompt_budget_tokens": 0,
+      "examples_after_sequence_filter": 285158,
+      "examples_before_sequence_filter": 285310,
+      "filter_stage_distributions": {
+        "after_disagreement_filter": {
+          "benchmark": {
+            "ChemLLMBench": 28771,
+            "Civil Service Examination": 7234,
+            "Data Analysis": 617,
+            "Date Arithmetic": 9167,
+            "GRE & GMAT": 3737,
+            "LSAT": 16530,
+            "Language": 470,
+            "MCTACO": 3734,
+            "MMLU-Pro": 98811,
+            "Math": 3001,
+            "MedCalcBench": 9804,
+            "MenatQA": 11777,
+            "OmniMath": 29517,
+            "Reasoning": 975,
+            "SAT": 7645,
+            "SciBench": 6360,
+            "TempReason": 11519,
+            "TimeDial": 6087,
+            "TimeQA": 13083,
+            "TruthQuest": 18972
+          },
+          "model_id": {
+            "DK-R1-Dist-Qwen-1.5B": 15314,
+            "DK-R1-Dist-Qwen-14B": 15352,
+            "DK-R1-Dist-Qwen-32B": 14922,
+            "DK-R1-Dist-Qwen-7B": 15215,
+            "gemini-2.5-flash": 14468,
+            "gemini-3-flash": 15106,
+            "gemini-3.1-pro": 15158,
+            "gpt-35-turbo": 15163,
+            "gpt-5.2": 14241,
+            "gpt4o": 16106,
+            "llama3d1-405b": 15418,
+            "llama3d2-11b": 15272,
+            "llama3d2-1b": 15274,
+            "llama3d2-3b": 15288,
+            "llama3d2-90b": 15393,
+            "llama4-17B-128E": 15161,
+            "o1-mini": 15358,
+            "o1_re=low": 15044,
+            "o3-mini": 14558
+          },
+          "num_examples": 287811,
+          "target_binary": {
+            "CORRECT": 192174,
+            "INCORRECT": 95637
+          },
+          "target_score": {
+            "1": 89963,
+            "2": 5674,
+            "3": 4685,
+            "4": 11341,
+            "5": 176148
+          },
+          "task": {
+            "AMPS_Hard": 1174,
+            "AQuA-RAT": 3737,
+            "Algebra": 5977,
+            "Applied Mathematics": 5444,
+            "Calculus": 535,
+            "Chemistry": 2539,
+            "Date Arithmetic": 9167,
+            "Discrete Mathematics": 5475,
+            "E": 6185,
+            "Geometry": 5928,
+            "I": 6651,
+            "LSAT-AR": 3290,
+            "LSAT-LR": 8608,
+            "LSAT-RC": 4632,
+            "LogiQA-en": 7234,
+            "MCTACO": 3734,
+            "Math": 1901,
+            "MenatQA-Counterfactual": 2172,
+            "MenatQA-Order": 2738,
+            "MenatQA-Scope": 6867,
+            "Number Theory": 5639,
+            "Physics": 1920,
+            "Precalculus": 519,
+            "S": 6136,
+            "SAT-En": 3643,
+            "SAT-Math": 4002,
+            "TempReason-L2": 5565,
+            "TempReason-L3": 5954,
+            "TimeDial": 6087,
+            "TimeQA-explicit": 6894,
+            "TimeQA-implicit": 6189,
+            "biology": 8307,
+            "business": 7478,
+            "chemistry": 6672,
+            "computer science": 6271,
+            "connections": 470,
+            "cta": 617,
+            "date": 491,
+            "diagnosis": 211,
+            "dosage": 372,
+            "economics": 7831,
+            "engineering": 5291,
+            "health": 7479,
+            "history": 5520,
+            "lab": 3165,
+            "law": 6462,
+            "math": 7719,
+            "math_comp": 1394,
+            "molecule_captioning": 2641,
+            "molecule_design": 4313,
+            "name_prediction": 8652,
+            "olympiad": 433,
+            "other": 7799,
+            "philosophy": 7334,
+            "physical": 3929,
+            "physics": 6828,
+            "psychology": 7820,
+            "reaction_prediction": 6929,
+            "retrosynthesis": 6236,
+            "risk": 1353,
+            "severity": 283,
+            "spatial": 582,
+            "zebra_puzzle": 393
+          }
+        },
+        "after_response_length_filter": {
+          "benchmark": {
+            "ChemLLMBench": 27913,
+            "Civil Service Examination": 7207,
+            "Data Analysis": 617,
+            "Date Arithmetic": 9167,
+            "GRE & GMAT": 3733,
+            "LSAT": 16471,
+            "Language": 468,
+            "MCTACO": 3733,
+            "MMLU-Pro": 98506,
+            "Math": 2951,
+            "MedCalcBench": 9799,
+            "MenatQA": 11762,
+            "OmniMath": 28488,
+            "Reasoning": 953,
+            "SAT": 7645,
+            "SciBench": 6270,
+            "TempReason": 11519,
+            "TimeDial": 6087,
+            "TimeQA": 13082,
+            "TruthQuest": 18939
+          },
+          "model_id": {
+            "DK-R1-Dist-Qwen-1.5B": 15302,
+            "DK-R1-Dist-Qwen-14B": 15351,
+            "DK-R1-Dist-Qwen-32B": 12577,
+            "DK-R1-Dist-Qwen-7B": 15128,
+            "gemini-2.5-flash": 14426,
+            "gemini-3-flash": 15104,
+            "gemini-3.1-pro": 15158,
+            "gpt-35-turbo": 15163,
+            "gpt-5.2": 14241,
+            "gpt4o": 16106,
+            "llama3d1-405b": 15418,
+            "llama3d2-11b": 15267,
+            "llama3d2-1b": 15272,
+            "llama3d2-3b": 15288,
+            "llama3d2-90b": 15393,
+            "llama4-17B-128E": 15159,
+            "o1-mini": 15358,
+            "o1_re=low": 15041,
+            "o3-mini": 14558
+          },
+          "num_examples": 285310,
+          "target_binary": {
+            "CORRECT": 191333,
+            "INCORRECT": 93977
+          },
+          "target_score": {
+            "1": 88379,
+            "2": 5598,
+            "3": 4641,
+            "4": 11284,
+            "5": 175408
+          },
+          "task": {
+            "AMPS_Hard": 1157,
+            "AQuA-RAT": 3733,
+            "Algebra": 5814,
+            "Applied Mathematics": 5309,
+            "Calculus": 516,
+            "Chemistry": 2502,
+            "Date Arithmetic": 9167,
+            "Discrete Mathematics": 5235,
+            "E": 6164,
+            "Geometry": 5695,
+            "I": 6647,
+            "LSAT-AR": 3234,
+            "LSAT-LR": 8605,
+            "LSAT-RC": 4632,
+            "LogiQA-en": 7207,
+            "MCTACO": 3733,
+            "Math": 1887,
+            "MenatQA-Counterfactual": 2166,
+            "MenatQA-Order": 2737,
+            "MenatQA-Scope": 6859,
+            "Number Theory": 5411,
+            "Physics": 1881,
+            "Precalculus": 508,
+            "S": 6128,
+            "SAT-En": 3643,
+            "SAT-Math": 4002,
+            "TempReason-L2": 5565,
+            "TempReason-L3": 5954,
+            "TimeDial": 6087,
+            "TimeQA-explicit": 6893,
+            "TimeQA-implicit": 6189,
+            "biology": 8294,
+            "business": 7469,
+            "chemistry": 6615,
+            "computer science": 6245,
+            "connections": 468,
+            "cta": 617,
+            "date": 491,
+            "diagnosis": 211,
+            "dosage": 372,
+            "economics": 7827,
+            "engineering": 5182,
+            "health": 7475,
+            "history": 5520,
+            "lab": 3163,
+            "law": 6454,
+            "math": 7692,
+            "math_comp": 1367,
+            "molecule_captioning": 2614,
+            "molecule_design": 4306,
+            "name_prediction": 8201,
+            "olympiad": 427,
+            "other": 7797,
+            "philosophy": 7330,
+            "physical": 3927,
+            "physics": 6787,
+            "psychology": 7819,
+            "reaction_prediction": 6768,
+            "retrosynthesis": 6024,
+            "risk": 1353,
+            "severity": 282,
+            "spatial": 572,
+            "zebra_puzzle": 381
+          }
+        },
+        "raw": {
+          "benchmark": {
+            "ChemLLMBench": 32694,
+            "Civil Service Examination": 7677,
+            "Data Analysis": 627,
+            "Date Arithmetic": 9365,
+            "GRE & GMAT": 3855,
+            "LSAT": 17145,
+            "Language": 550,
+            "MCTACO": 3891,
+            "MMLU-Pro": 102896,
+            "Math": 3263,
+            "MedCalcBench": 10453,
+            "MenatQA": 12674,
+            "OmniMath": 31272,
+            "Reasoning": 1056,
+            "SAT": 7752,
+            "SciBench": 6728,
+            "TempReason": 12318,
+            "TimeDial": 6412,
+            "TimeQA": 13681,
+            "TruthQuest": 20037
+          },
+          "model_id": {
+            "DK-R1-Dist-Qwen-1.5B": 16108,
+            "DK-R1-Dist-Qwen-14B": 16108,
+            "DK-R1-Dist-Qwen-32B": 16069,
+            "DK-R1-Dist-Qwen-7B": 16108,
+            "gemini-2.5-flash": 15785,
+            "gemini-3-flash": 16045,
+            "gemini-3.1-pro": 15981,
+            "gpt-35-turbo": 16100,
+            "gpt-5.2": 15050,
+            "gpt4o": 16106,
+            "llama3d1-405b": 16108,
+            "llama3d2-11b": 16108,
+            "llama3d2-1b": 16107,
+            "llama3d2-3b": 16108,
+            "llama3d2-90b": 16108,
+            "llama4-17B-128E": 16041,
+            "o1-mini": 16108,
+            "o1_re=low": 16108,
+            "o3-mini": 16090
+          },
+          "num_examples": 304346,
+          "target_binary": {
+            "CORRECT": 201528,
+            "INCORRECT": 102818
+          },
+          "target_score": {
+            "1": 89963,
+            "2": 12855,
+            "3": 13029,
+            "4": 12351,
+            "5": 176148
+          },
+          "task": {
+            "AMPS_Hard": 1292,
+            "AQuA-RAT": 3855,
+            "Algebra": 6331,
+            "Applied Mathematics": 5697,
+            "Calculus": 565,
+            "Chemistry": 2694,
+            "Date Arithmetic": 9365,
+            "Discrete Mathematics": 5861,
+            "E": 6532,
+            "Geometry": 6215,
+            "I": 7045,
+            "LSAT-AR": 3535,
+            "LSAT-LR": 8868,
+            "LSAT-RC": 4742,
+            "LogiQA-en": 7677,
+            "MCTACO": 3891,
+            "Math": 1988,
+            "MenatQA-Counterfactual": 2440,
+            "MenatQA-Order": 2925,
+            "MenatQA-Scope": 7309,
+            "Number Theory": 6035,
+            "Physics": 2046,
+            "Precalculus": 568,
+            "S": 6460,
+            "SAT-En": 3686,
+            "SAT-Math": 4066,
+            "TempReason-L2": 5960,
+            "TempReason-L3": 6358,
+            "TimeDial": 6412,
+            "TimeQA-explicit": 7137,
+            "TimeQA-implicit": 6544,
+            "biology": 8483,
+            "business": 7783,
+            "chemistry": 6981,
+            "computer science": 6542,
+            "connections": 550,
+            "cta": 627,
+            "date": 513,
+            "diagnosis": 266,
+            "dosage": 380,
+            "economics": 8104,
+            "engineering": 5614,
+            "health": 7793,
+            "history": 5729,
+            "lab": 3357,
+            "law": 6797,
+            "math": 8070,
+            "math_comp": 1480,
+            "molecule_captioning": 3040,
+            "molecule_design": 5585,
+            "name_prediction": 9036,
+            "olympiad": 491,
+            "other": 8129,
+            "philosophy": 7617,
+            "physical": 4029,
+            "physics": 7160,
+            "psychology": 8094,
+            "reaction_prediction": 7819,
+            "retrosynthesis": 7214,
+            "risk": 1587,
+            "severity": 321,
+            "spatial": 638,
+            "zebra_puzzle": 418
+          }
+        }
+      },
+      "kept_prompt_token_length": {
+        "max": 4093,
+        "mean": 853.0326345394483,
+        "min": 252,
+        "p50": 769.0,
+        "p75": 988.0,
+        "p90": 1330.0,
+        "p95": 1659.0,
+        "p99": 2596.0
+      },
+      "kept_sequence_length": {
+        "max": 4095,
+        "mean": 855.0326345394483,
+        "min": 254,
+        "p50": 771.0,
+        "p75": 990.0,
+        "p90": 1332.0,
+        "p95": 1661.0,
+        "p99": 2598.0
+      },
+      "length_filter_warnings": [
+        "max_response_tokens is greater than or equal to max_seq_length; examples can pass the response cap while having no room for the formatted prompt.",
+        "Effective prompt budget is only 0 tokens after reserving the response cap; consider increasing training.max_seq_length."
+      ],
+      "max_disagreement": 1,
+      "max_response_tokens": 4096,
+      "max_seq_length": 4096,
+      "on_sequence_overflow": "skip",
+      "overflowed_response_token_length": {
+        "max": 4096,
+        "mean": 3629.6052631578946,
+        "min": 1582,
+        "p50": 3875.5,
+        "p75": 3996.5,
+        "p90": 4051.0,
+        "p95": 4075.6,
+        "p99": 4091.45
+      },
+      "raw_examples": 304346,
+      "removed_by_disagreement": 16535,
+      "removed_by_disagreement_pct": 5.432961169195587,
+      "removed_by_response_length": 2501,
+      "removed_by_response_length_pct": 0.8689730413361546,
+      "sequence_overflow_count": 152,
+      "sequence_overflow_pct": 0.05327538466930706,
+      "sequence_overflow_reason": "Full chat-formatted sequence exceeded max_seq_length after response filtering. This includes system prompt, question, reference answer, model response, and chat-template tokens, plus target score tokens."
+    },
+    "inference_config.yaml": {
+      "data": {
+        "columns": {
+          "benchmark": "benchmark",
+          "example_id": "instance_id",
+          "judge_1_score": "score_gpt4o",
+          "judge_2_score": "score_sonnet",
+          "model_id": "model_id",
+          "question": "question",
+          "reference_answer": "ground_truth",
+          "response": "response",
+          "source": "source",
+          "task": "task"
+        },
+        "filters": {
+          "max_disagreement": 1,
+          "max_response_tokens": 4096,
+          "on_sequence_overflow": "skip"
+        },
+        "path": "data/processed/response_scores.parquet",
+        "prepared_dir": null,
+        "preprocessing_num_workers": 5,
+        "token_length_batch_size": 2048,
+        "tokenizers_parallelism": true
+      },
+      "distributed": {
+        "backend": "nccl",
+        "deepspeed": {
+          "config_overrides": {},
+          "gradient_clipping": "auto",
+          "offload_optimizer_device": "none",
+          "offload_param_device": "none",
+          "stage3_gather_16bit_weights_on_model_save": true,
+          "zero_stage": 2
+        },
+        "enabled": true,
+        "find_unused_parameters": false,
+        "fsdp": {
+          "activation_checkpointing": true,
+          "sharding_strategy": "full_shard",
+          "transformer_layer_cls_to_wrap": null,
+          "use_orig_params": true
+        },
+        "gradient_checkpointing": true,
+        "mixed_precision": "bf16",
+        "strategy": "ddp"
+      },
+      "evaluation": {
+        "length_buckets": [
+          0,
+          256,
+          512,
+          1024,
+          2048,
+          3072,
+          4096,
+          1000000000
+        ]
+      },
+      "hub": {
+        "commit_message": "Upload ADeLe distilled judge",
+        "create_pr": false,
+        "local_checkpoint_dir": null,
+        "max_shard_size": "5GB",
+        "output_staging_dir": null,
+        "private": false,
+        "repo_id": null
+      },
+      "inference": {
+        "allow_base_model": true,
+        "allowed_scores": [
+          "1",
+          "2",
+          "3",
+          "4",
+          "5"
+        ],
+        "batch_size": 64,
+        "binary_threshold": 3,
+        "generation_fallback": false,
+        "method": "restricted_continuation_logprobs_fast",
+        "require_adapter": false
+      },
+      "model": {
+        "adapter_path": "runs/qwen3_14b_restricted_score_ce/adapter",
+        "attn_implementation": "sdpa",
+        "model_name_or_path": "Qwen/Qwen3-14B",
+        "revision": null,
+        "thinking_mode": {
+          "apply_if_supported": true,
+          "enabled": false
+        },
+        "trust_remote_code": true
+      },
+      "project": {
+        "output_dir": "runs/qwen3_14b_restricted_score_ce",
+        "run_name": "qwen3_14b_restricted_score_ce",
+        "seed": 42
+      },
+      "prompt": {
+        "system_prompt": "You are an answer quality evaluator. You will receive a question, a reference\nanswer, and a model response, each delimited by ### headers.\n\nRate the model response on the following scale:\n1 - Surely incorrect: the response is wrong or completely misses the point.\n2 - Likely incorrect: the response has significant errors or critical omissions.\n3 - Minimally correct / sufficient: the response is partially correct or borderline.\n4 - Likely correct: the response is mostly correct with minor issues.\n5 - Surely correct: the response is fully correct and complete.\n\nRules:\n- Base your rating strictly on correctness relative to the reference answer.\n- Ignore writing style, verbosity, or formatting unless they affect correctness.\n- If the final answer is correct but the reasoning contains substantive errors, lower the rating according to the severity of those errors.\n- Output only a single integer from 1 to 5. No explanation. No punctuation.\n"
+      },
+      "split": {
+        "held_out_model": null,
+        "lomo_validation_fraction": 0.05,
+        "lomo_validation_max_examples": 30000,
+        "lomo_validation_seed": 42,
+        "mode": "fixed_by_model",
+        "train_models": "auto_except_val_test",
+        "validation_models": [
+          "gemini-3-flash",
+          "DK-R1-Dist-Qwen-14B",
+          "llama3d2-3b"
+        ]
+      },
+      "training": {
+        "cache_tokenized_datasets": true,
+        "class_weighting": null,
+        "dtype": "bfloat16",
+        "eval_steps": 500,
+        "eval_subset_seed": 42,
+        "eval_subset_size": null,
+        "eval_subset_strategy": "stratified",
+        "eval_subset_stratify_columns": [
+          "model_id",
+          "target_score"
+        ],
+        "gradient_accumulation_steps": 4,
+        "learning_rate": 3e-05,
+        "length_column_name": "length",
+        "load_in_4bit": true,
+        "logging_steps": 10,
+        "lora_alpha": 64,
+        "lora_dropout": 0.0,
+        "lora_r": 32,
+        "loss": {
+          "class_weights": null,
+          "lambda_binary": 0.5,
+          "type": "ce_5way"
+        },
+        "lr_scheduler_type": "cosine",
+        "max_grad_norm": 1.0,
+        "max_seq_length": 4096,
+        "num_train_epochs": 1,
+        "objective": "restricted_score_ce",
+        "optim": "adamw_8bit",
+        "packing": false,
+        "per_device_eval_batch_size": 2,
+        "per_device_train_batch_size": 2,
+        "resume_from_checkpoint": null,
+        "save_steps": 500,
+        "save_total_limit": 10,
+        "score_class_weights": null,
+        "seed": 42,
+        "target_modules": "auto",
+        "train_sampling_strategy": "random",
+        "warmup_ratio": 0.03,
+        "weight_decay": 0.0
+      }
+    },
+    "length_statistics.json": {
+      "num_examples": 285158,
+      "prompt_token_length": {
+        "max": 4093,
+        "mean": 853.0326345394483,
+        "min": 252,
+        "p50": 769.0,
+        "p75": 988.0,
+        "p90": 1330.0,
+        "p95": 1659.0,
+        "p99": 2596.0
+      },
+      "response_token_length": {
+        "max": 3803,
+        "mean": 397.55135047938336,
+        "min": 0,
+        "p50": 307.0,
+        "p75": 508.0,
+        "p90": 789.0,
+        "p95": 1116.0,
+        "p99": 2162.0
+      },
+      "sequence_length": {
+        "max": 4095,
+        "mean": 855.0326345394483,
+        "min": 254,
+        "p50": 771.0,
+        "p75": 990.0,
+        "p90": 1332.0,
+        "p95": 1661.0,
+        "p99": 2598.0
+      },
+      "target_token_length": {
+        "max": 1,
+        "mean": 1.0,
+        "min": 1,
+        "p50": 1.0,
+        "p75": 1.0,
+        "p90": 1.0,
+        "p95": 1.0,
+        "p99": 1.0
+      }
+    },
+    "run_metadata.json": {
+      "distributed": {
+        "backend": "nccl",
+        "deepspeed": {
+          "config_overrides": {},
+          "gradient_clipping": "auto",
+          "offload_optimizer_device": "none",
+          "offload_param_device": "none",
+          "stage3_gather_16bit_weights_on_model_save": true,
+          "zero_stage": 2
+        },
+        "effective_global_batch_size": 64,
+        "enabled": true,
+        "find_unused_parameters": false,
+        "fsdp": {
+          "activation_checkpointing": true,
+          "sharding_strategy": "full_shard",
+          "transformer_layer_cls_to_wrap": null,
+          "use_orig_params": true
+        },
+        "gradient_accumulation_steps": 4,
+        "gradient_checkpointing": true,
+        "launcher": "torchrun",
+        "mixed_precision": "bf16",
+        "per_device_train_batch_size": 2,
+        "strategy": "ddp",
+        "world_size": 8
+      },
+      "effective_global_batch_size": 64,
+      "evaluation_enabled": true,
+      "git_commit": "70ddf4477faac49d4c1d9eb87cbefb58fab7e4a0",
+      "package_versions": {
+        "accelerate": "1.13.0",
+        "bitsandbytes": "0.49.2",
+        "datasets": "4.3.0",
+        "deepspeed": "unavailable",
+        "peft": "0.19.1",
+        "python": "3.11.15",
+        "torch": "2.7.1+cu118",
+        "transformers": "5.5.0",
+        "trl": "0.24.0",
+        "unsloth": "2026.4.8"
+      },
+      "score_class_weights": null,
+      "score_token_ids": [
+        16,
+        17,
+        18,
+        19,
+        20
+      ],
+      "source_split_counts": {
+        "test": 0,
+        "train": 239420,
+        "validation": 45738
+      },
+      "training_backend": "transformers_peft",
+      "training_examples": 239420,
+      "training_loss": {
+        "class_weights": null,
+        "lambda_binary": 0.5,
+        "type": "ce_5way"
+      },
+      "training_mode": "standard",
+      "training_objective": "restricted_score_ce",
+      "validation_full_examples": 45738,
+      "validation_monitor_examples": 45738,
+      "warmup": {
+        "total_optimization_steps": 3741,
+        "warmup_ratio": 0.03,
+        "warmup_steps": 113
+      },
+      "world_size": 8
+    },
+    "score_tokenization_report.json": [
+      {
+        "num_tokens": 1,
+        "score": "1",
+        "token_ids": [
+          16
+        ],
+        "tokens": [
+          "1"
+        ]
+      },
+      {
+        "num_tokens": 1,
+        "score": "2",
+        "token_ids": [
+          17
+        ],
+        "tokens": [
+          "2"
+        ]
+      },
+      {
+        "num_tokens": 1,
+        "score": "3",
+        "token_ids": [
+          18
+        ],
+        "tokens": [
+          "3"
+        ]
+      },
+      {
+        "num_tokens": 1,
+        "score": "4",
+        "token_ids": [
+          19
+        ],
+        "tokens": [
+          "4"
+        ]
+      },
+      {
+        "num_tokens": 1,
+        "score": "5",
+        "token_ids": [
+          20
+        ],
+        "tokens": [
+          "5"
+        ]
+      }
+    ],
+    "split_report.json": {
+      "test": {
+        "examples": 0,
+        "models": [],
+        "num_models": 0
+      },
+      "train": {
+        "examples": 239420,
+        "models": [
+          "DK-R1-Dist-Qwen-1.5B",
+          "DK-R1-Dist-Qwen-32B",
+          "DK-R1-Dist-Qwen-7B",
+          "gemini-2.5-flash",
+          "gemini-3.1-pro",
+          "gpt-35-turbo",
+          "gpt-5.2",
+          "gpt4o",
+          "llama3d1-405b",
+          "llama3d2-11b",
+          "llama3d2-1b",
+          "llama3d2-90b",
+          "llama4-17B-128E",
+          "o1-mini",
+          "o1_re=low",
+          "o3-mini"
+        ],
+        "num_models": 16
+      },
+      "validation": {
+        "examples": 45738,
+        "models": [
+          "DK-R1-Dist-Qwen-14B",
+          "gemini-3-flash",
+          "llama3d2-3b"
+        ],
+        "num_models": 3
+      }
+    },
+    "train_metrics.json": {
+      "epoch": 1.0,
+      "total_flos": 2.185247058507386e+19,
+      "train_loss": 0.6326745578038823,
+      "train_runtime": 128852.3134,
+      "train_samples_per_second": 1.858,
+      "train_steps_per_second": 0.029
+    },
+    "validation_trainer_metrics.json": {
+      "epoch": 1.0,
+      "eval_binary_accuracy": 0.9893523984433076,
+      "eval_binary_macro_f1": 0.9880204659010172,
+      "eval_confidence_mean": 0.9603744832085106,
+      "eval_confidence_p50": 0.9991409778594971,
+      "eval_confidence_p90": 0.9999487400054932,
+      "eval_expected_calibration_error_10bin": 0.004097698586483999,
+      "eval_f1_correct": 0.9920149535162078,
+      "eval_f1_incorrect": 0.9840259782858267,
+      "eval_f1_score_1": 0.9774369762155193,
+      "eval_f1_score_2": 0.38461538461538464,
+      "eval_f1_score_3": 0.5938009787928223,
+      "eval_f1_score_4": 0.730398069963812,
+      "eval_f1_score_5": 0.989033961060818,
+      "eval_false_negative_rate_correct": 0.009138552243694727,
+      "eval_false_positive_rate_correct": 0.013677012098895318,
+      "eval_loss": 0.09880143404006958,
+      "eval_num_examples": 45738,
+      "eval_ordinal_accuracy": 0.963924963924964,
+      "eval_ordinal_macro_f1": 0.7350570741296714,
+      "eval_ordinal_mae": 0.04779395688486598,
+      "eval_precision_correct": 0.9931711481007256,
+      "eval_precision_incorrect": 0.98173964264677,
+      "eval_precision_score_1": 0.9729145558932792,
+      "eval_precision_score_2": 0.41139240506329117,
+      "eval_precision_score_3": 0.6159052453468697,
+      "eval_precision_score_4": 0.7802835051546392,
+      "eval_precision_score_5": 0.9858030795310072,
+      "eval_pred_binary_counts": {
+        "CORRECT": 30459,
+        "INCORRECT": 15279
+      },
+      "eval_pred_score_counts": {
+        "1": 14805,
+        "2": 474,
+        "3": 591,
+        "4": 1552,
+        "5": 28316
+      },
+      "eval_recall_correct": 0.9908614477563052,
+      "eval_recall_incorrect": 0.9863229879011047,
+      "eval_recall_score_1": 0.9820016362148896,
+      "eval_recall_score_2": 0.3611111111111111,
+      "eval_recall_score_3": 0.573228346456693,
+      "eval_recall_score_4": 0.6865079365079365,
+      "eval_recall_score_5": 0.9922860900785611,
+      "eval_runtime": 4341.2041,
+      "eval_samples_per_second": 10.536,
+      "eval_score_entropy_mean": 0.10761874169111252,
+      "eval_score_margin_mean": 6.721137046813965,
+      "eval_steps_per_second": 0.659,
+      "eval_support_correct": 30530,
+      "eval_support_incorrect": 15208,
+      "eval_support_score_1": 14668,
+      "eval_support_score_2": 540,
+      "eval_support_score_3": 635,
+      "eval_support_score_4": 1764,
+      "eval_support_score_5": 28131,
+      "eval_target_score_counts": {
+        "1": 14668,
+        "2": 540,
+        "3": 635,
+        "4": 1764,
+        "5": 28131
+      },
+      "eval_within_1_accuracy": 0.993244129607766
+    }
+  },
+  "base_model": "Qwen/Qwen3-14B",
+  "binary_threshold": 3,
+  "git_commit": "8a6e08f6f071ce154a27e2718a55ad33895348c6",
+  "max_seq_length": 4096,
+  "package_versions": {
+    "accelerate": "1.13.0",
+    "bitsandbytes": "0.49.2",
+    "datasets": "4.3.0",
+    "deepspeed": "unavailable",
+    "peft": "0.19.1",
+    "python": "3.11.15",
+    "torch": "2.7.1+cu118",
+    "transformers": "5.5.0",
+    "trl": "0.24.0",
+    "unsloth": "2026.4.8"
+  },
+  "repo_id": "adgomant/adele-judge-qwen3-14-cre",
+  "run_dir": "runs/qwen3_14b_restricted_score_ce",
+  "thinking_mode": {
+    "apply_if_supported": true,
+    "enabled": false
+  },
+  "training_objective": "restricted_score_ce"
+}
\ No newline at end of file
diff --git a/adele_judge_pipeline.py b/adele_judge_pipeline.py
new file mode 100644
index 0000000..f3f047c
--- /dev/null
+++ b/adele_judge_pipeline.py
@@ -0,0 +1,304 @@
+from __future__ import annotations
+
+import inspect
+import json
+from pathlib import Path
+from typing import Any
+
+from transformers import Pipeline
+
+
+THINKING_KWARG = "enable_thinking"
+DEFAULT_SYSTEM_PROMPT = "Return only one score from 1 to 5. Do not explain."
+DEFAULT_ALLOWED_SCORES = ["1", "2", "3", "4", "5"]
+DEFAULT_BINARY_THRESHOLD = 3
+
+
+def load_adele_judge_config(repo_id_or_path: str) -> dict[str, Any]:
+    path = Path(repo_id_or_path) / "adele_judge_config.json"
+    if path.exists():
+        return json.loads(path.read_text(encoding="utf-8"))
+
+    from huggingface_hub import hf_hub_download
+
+    downloaded = hf_hub_download(repo_id_or_path, "adele_judge_config.json")
+    return json.loads(Path(downloaded).read_text(encoding="utf-8"))
+
+
+def load_adele_judge_config_or_default(model: Any, tokenizer: Any) -> dict[str, Any]:
+    candidates = [
+        getattr(model, "name_or_path", None),
+        getattr(getattr(model, "config", None), "_name_or_path", None),
+        getattr(tokenizer, "name_or_path", None),
+        getattr(tokenizer, "_name_or_path", None),
+    ]
+    for candidate in candidates:
+        if not candidate:
+            continue
+        try:
+            return load_adele_judge_config(str(candidate))
+        except Exception:
+            continue
+    return {}
+
+
+def adele_judge_settings(config: dict[str, Any] | None) -> dict[str, Any]:
+    config = config or {}
+    prompt_config = config.get("prompt", {}) if isinstance(config.get("prompt"), dict) else {}
+    inference_config = (
+        config.get("inference", {}) if isinstance(config.get("inference"), dict) else {}
+    )
+    model_config = config.get("model", {}) if isinstance(config.get("model"), dict) else {}
+    return {
+        "system_prompt": prompt_config.get("system_prompt") or DEFAULT_SYSTEM_PROMPT,
+        "allowed_scores": [
+            str(score)
+            for score in inference_config.get("allowed_scores", DEFAULT_ALLOWED_SCORES)
+        ],
+        "binary_threshold": int(
+            inference_config.get("binary_threshold", DEFAULT_BINARY_THRESHOLD)
+        ),
+        "thinking_mode": model_config.get("thinking_mode") or {},
+    }
+
+
+def clean_value(value: Any, fallback: str = "N/A") -> str:
+    if value is None:
+        return fallback
+    text = str(value)
+    if not text or text.lower() == "nan":
+        return fallback
+    return text
+
+
+def validate_example(inputs: Any) -> dict[str, Any]:
+    if not isinstance(inputs, dict):
+        raise ValueError("ADeLe judge input must be a mapping")
+
+    missing = []
+    if inputs.get("question") is None:
+        missing.append("question")
+    if inputs.get("model_response") is None:
+        missing.append("model_response")
+    reference_answer = inputs.get("reference_answer")
+    if reference_answer is None:
+        reference_answer = inputs.get("ground_truth")
+    if reference_answer is None:
+        missing.append("reference_answer or ground_truth")
+    if missing:
+        raise ValueError(f"Missing required field(s): {', '.join(missing)}")
+
+    return {
+        "question": inputs["question"],
+        "reference_answer": reference_answer,
+        "model_response": inputs["model_response"],
+    }
+
+
+def build_user_message(example: dict[str, Any]) -> str:
+    return "\n\n".join(
+        [
+            f"### QUESTION\n{clean_value(example.get('question'))}",
+            f"### REFERENCE ANSWER\n{clean_value(example.get('reference_answer'))}",
+            f"### MODEL RESPONSE\n{clean_value(example.get('model_response'), fallback='')}",
+            "### SCORE\n",
+        ]
+    )
+
+
+def build_messages(example: dict[str, Any], system_prompt: str) -> list[dict[str, str]]:
+    return [
+        {"role": "system", "content": system_prompt.strip()},
+        {"role": "user", "content": build_user_message(example)},
+    ]
+
+
+def chat_template_supports_thinking(tokenizer: Any) -> bool:
+    apply_chat_template = getattr(tokenizer, "apply_chat_template", None)
+    if apply_chat_template is None:
+        return False
+    try:
+        signature = inspect.signature(apply_chat_template)
+    except (TypeError, ValueError):
+        return False
+    accepts_kwarg = any(
+        parameter.kind == inspect.Parameter.VAR_KEYWORD or name == THINKING_KWARG
+        for name, parameter in signature.parameters.items()
+    )
+    if not accepts_kwarg:
+        return False
+
+    template = getattr(tokenizer, "chat_template", None)
+    if isinstance(template, str) and THINKING_KWARG in template:
+        return True
+
+    candidates = [
+        getattr(tokenizer, "name_or_path", None),
+        getattr(tokenizer, "_name_or_path", None),
+        getattr(tokenizer, "model_name", None),
+    ]
+    init_kwargs = getattr(tokenizer, "init_kwargs", None)
+    if isinstance(init_kwargs, dict):
+        candidates.extend([init_kwargs.get("name_or_path"), init_kwargs.get("tokenizer_file")])
+    return any("qwen3" in str(candidate).lower() for candidate in candidates if candidate)
+
+
+def apply_chat_template_safe(
+    tokenizer: Any,
+    messages: list[dict[str, str]],
+    *,
+    add_generation_prompt: bool,
+    thinking_mode: dict[str, Any],
+) -> str:
+    if hasattr(tokenizer, "apply_chat_template") and getattr(tokenizer, "chat_template", None):
+        template_kwargs = {}
+        enabled = thinking_mode.get("enabled")
+        if (
+            enabled is not None
+            and bool(thinking_mode.get("apply_if_supported", True))
+            and chat_template_supports_thinking(tokenizer)
+        ):
+            template_kwargs[THINKING_KWARG] = bool(enabled)
+        return tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=add_generation_prompt,
+            **template_kwargs,
+        )
+
+    rendered = [f"<|{message['role']}|>\n{message['content']}" for message in messages]
+    if add_generation_prompt:
+        rendered.append("<|assistant|>\n")
+    return "\n".join(rendered)
+
+
+def encode_text(tokenizer: Any, text: str) -> list[int]:
+    return tokenizer(text, add_special_tokens=False, truncation=False)["input_ids"]
+
+
+def single_score_token_ids(tokenizer: Any, allowed_scores: list[str]) -> list[int]:
+    token_ids = [encode_text(tokenizer, score) for score in allowed_scores]
+    multi_token_scores = [
+        score for score, ids in zip(allowed_scores, token_ids, strict=True) if len(ids) != 1
+    ]
+    if multi_token_scores:
+        raise ValueError(
+            "ADeLeJudgePipeline requires score continuations to be single tokens; "
+            f"multi-token scores: {multi_token_scores}"
+        )
+    return [ids[0] for ids in token_ids]
+
+
+class ADeLeJudgePipeline(Pipeline):
+    """HF-native custom pipeline for restricted ADeLe judge scoring."""
+
+    def __init__(
+        self,
+        *args: Any,
+        adele_config: dict[str, Any] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(*args, **kwargs)
+        if self.tokenizer is None:
+            raise ValueError("ADeLeJudgePipeline requires a tokenizer")
+        if getattr(self.tokenizer, "pad_token", None) is None:
+            self.tokenizer.pad_token = getattr(self.tokenizer, "eos_token", None)
+
+        settings = adele_judge_settings(
+            adele_config
+            if adele_config is not None
+            else load_adele_judge_config_or_default(self.model, self.tokenizer)
+        )
+        self.system_prompt = settings["system_prompt"]
+        self.allowed_scores = settings["allowed_scores"]
+        self.binary_threshold = settings["binary_threshold"]
+        self.thinking_mode = settings["thinking_mode"]
+        self.score_token_ids = single_score_token_ids(self.tokenizer, self.allowed_scores)
+
+        if hasattr(self.model, "eval"):
+            self.model.eval()
+
+    def _sanitize_parameters(
+        self,
+        **kwargs: Any,
+    ) -> tuple[dict[str, Any], dict[str, Any], dict[str, Any]]:
+        return {}, {}, {}
+
+    def preprocess(self, inputs: Any) -> dict[str, Any]:
+        import torch
+
+        example = validate_example(inputs)
+        prompt = apply_chat_template_safe(
+            self.tokenizer,
+            build_messages(example, self.system_prompt),
+            add_generation_prompt=True,
+            thinking_mode=self.thinking_mode,
+        )
+        encoded = self.tokenizer(
+            prompt,
+            add_special_tokens=False,
+            truncation=False,
+            return_tensors="pt",
+        )
+        if "attention_mask" not in encoded:
+            encoded["attention_mask"] = torch.ones_like(encoded["input_ids"])
+        return {"input_ids": encoded["input_ids"], "attention_mask": encoded["attention_mask"]}
+
+    def _forward(self, model_inputs: dict[str, Any]) -> dict[str, Any]:
+        import torch
+        import torch.nn.functional as F
+
+        input_ids = model_inputs["input_ids"]
+        attention_mask = model_inputs["attention_mask"]
+        with torch.no_grad():
+            outputs = self.model(input_ids=input_ids, attention_mask=attention_mask)
+
+        token_positions = torch.arange(input_ids.shape[1], device=input_ids.device).unsqueeze(0)
+        positions = (attention_mask * token_positions).max(dim=1).values.to(dtype=torch.long)
+        batch_indices = torch.arange(input_ids.shape[0], device=input_ids.device)
+        final_logits = outputs.logits[batch_indices, positions]
+
+        score_ids = torch.tensor(self.score_token_ids, dtype=torch.long, device=final_logits.device)
+        score_logits = final_logits[:, score_ids]
+        logprobs = F.log_softmax(score_logits, dim=-1)
+        return {
+            "score_indices": torch.argmax(logprobs, dim=-1),
+            "probs": torch.exp(logprobs),
+            "logprobs": logprobs,
+        }
+
+    def postprocess(self, model_outputs: dict[str, Any]) -> dict[str, Any]:
+        import torch
+
+        score_index = int(model_outputs["score_indices"].reshape(-1)[0])
+        probs_tensor = model_outputs["probs"].reshape(-1, len(self.allowed_scores))[0]
+        logprobs_tensor = model_outputs["logprobs"].reshape(-1, len(self.allowed_scores))[0]
+
+        probs = {
+            score: float(prob)
+            for score, prob in zip(self.allowed_scores, probs_tensor.tolist(), strict=True)
+        }
+        logprobs = {
+            score: float(logprob)
+            for score, logprob in zip(self.allowed_scores, logprobs_tensor.tolist(), strict=True)
+        }
+
+        score = int(self.allowed_scores[score_index])
+        sorted_logprobs = torch.sort(logprobs_tensor).values
+        margin = (
+            float(sorted_logprobs[-1] - sorted_logprobs[-2])
+            if len(sorted_logprobs) > 1
+            else 0.0
+        )
+        entropy = float(
+            -(probs_tensor * torch.log(torch.clamp(probs_tensor, min=1e-12))).sum()
+        )
+        return {
+            "score": score,
+            "label": "CORRECT" if score >= self.binary_threshold else "INCORRECT",
+            "probs": probs,
+            "logprobs": logprobs,
+            "confidence": max(probs.values()),
+            "margin": margin,
+            "entropy": entropy,
+        }
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..01be9b3
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].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" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|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 %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- 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' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..f413f90
--- /dev/null
+++ b/config.json
@@ -0,0 +1,85 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "custom_pipelines": {
+    "adele-judge": {
+      "impl": "adele_judge_pipeline.ADeLeJudgePipeline",
+      "pt": [
+        "AutoModelForCausalLM"
+      ],
+      "tf": [],
+      "type": "text"
+    }
+  },
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..efab52f
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,5 @@
+{
+  "do_sample": false,
+  "max_new_tokens": 1,
+  "num_beams": 1
+}
\ No newline at end of file
diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors
new file mode 100644
index 0000000..b0c81ba
--- /dev/null
+++ b/model-00001-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5739c7705041195574706abc2af5e12c66c2281e1a93dd1419dd2439c0fd1a41
+size 4978180848
diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors
new file mode 100644
index 0000000..59c4216
--- /dev/null
+++ b/model-00002-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418628dcaf69131e39dff0aa22339698bf3111fd402a0c677ff8b1fb08a146de
+size 4917988408
diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors
new file mode 100644
index 0000000..9f0f555
--- /dev/null
+++ b/model-00003-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e63ccd5fd8e91297f66be63117190fbe6c5ad636c669d33263f490c42270e3a
+size 4991388720
diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors
new file mode 100644
index 0000000..8f5bc9d
--- /dev/null
+++ b/model-00004-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483606985498d68d803f7761870f76b0df2965034149f2d4af7f7c93bf707c3b
+size 4917988496
diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors
new file mode 100644
index 0000000..3d40832
--- /dev/null
+++ b/model-00005-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd0b2c97fb9d8fda9360f6293ccf899914f43d54ab8bcba3557ac62412451bd
+size 4991388720
diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors
new file mode 100644
index 0000000..b8830fc
--- /dev/null
+++ b/model-00006-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2e7fd55cd67b4370f657b6f1d3ee9673f8a8657e4a90eaf873bed6661744ad
+size 4739730440
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..8d53005
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,451 @@
+{
+  "metadata": {
+    "total_parameters": 14768307200,
+    "total_size": 29536614400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..c7afbed
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..9fd0fb4
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/training_config.yaml b/training_config.yaml
new file mode 100644
index 0000000..7bc69c3
--- /dev/null
+++ b/training_config.yaml
@@ -0,0 +1,168 @@
+project:
+  run_name: qwen3_14b_restricted_score_ce
+  output_dir: runs/qwen3_14b_restricted_score_ce
+  seed: 42
+data:
+  path: data/processed/response_scores.parquet
+  prepared_dir: null
+  columns:
+    question: question
+    reference_answer: ground_truth
+    response: response
+    judge_1_score: score_gpt4o
+    judge_2_score: score_sonnet
+    model_id: model_id
+    benchmark: benchmark
+    task: task
+    example_id: instance_id
+    source: source
+  filters:
+    max_disagreement: 1
+    max_response_tokens: 4096
+    on_sequence_overflow: skip
+  preprocessing_num_workers: 40
+  tokenizers_parallelism: true
+  token_length_batch_size: 2048
+model:
+  model_name_or_path: Qwen/Qwen3-14B
+  revision: null
+  attn_implementation: sdpa
+  adapter_path: null
+  trust_remote_code: true
+  thinking_mode:
+    enabled: false
+    apply_if_supported: true
+prompt:
+  system_prompt: 'You are an answer quality evaluator. You will receive a question,
+    a reference
+
+    answer, and a model response, each delimited by ### headers.
+
+
+    Rate the model response on the following scale:
+
+    1 - Surely incorrect: the response is wrong or completely misses the point.
+
+    2 - Likely incorrect: the response has significant errors or critical omissions.
+
+    3 - Minimally correct / sufficient: the response is partially correct or borderline.
+
+    4 - Likely correct: the response is mostly correct with minor issues.
+
+    5 - Surely correct: the response is fully correct and complete.
+
+
+    Rules:
+
+    - Base your rating strictly on correctness relative to the reference answer.
+
+    - Ignore writing style, verbosity, or formatting unless they affect correctness.
+
+    - If the final answer is correct but the reasoning contains substantive errors,
+    lower the rating according to the severity of those errors.
+
+    - Output only a single integer from 1 to 5. No explanation. No punctuation.
+
+    '
+split:
+  mode: fixed_by_model
+  validation_models:
+  - gemini-3-flash
+  - DK-R1-Dist-Qwen-14B
+  - llama3d2-3b
+  train_models: auto_except_val_test
+  held_out_model: null
+  lomo_validation_fraction: 0.05
+  lomo_validation_max_examples: 30000
+  lomo_validation_seed: 42
+training:
+  max_seq_length: 4096
+  load_in_4bit: true
+  dtype: bfloat16
+  objective: restricted_score_ce
+  loss:
+    type: ce_5way
+    lambda_binary: 0.5
+    class_weights: null
+  class_weighting: null
+  score_class_weights: null
+  lora_r: 32
+  lora_alpha: 64
+  lora_dropout: 0.0
+  target_modules: auto
+  learning_rate: 3.0e-05
+  num_train_epochs: 1
+  per_device_train_batch_size: 2
+  per_device_eval_batch_size: 2
+  gradient_accumulation_steps: 4
+  warmup_ratio: 0.03
+  lr_scheduler_type: cosine
+  weight_decay: 0.0
+  optim: adamw_8bit
+  packing: false
+  cache_tokenized_datasets: true
+  eval_subset_size: null
+  eval_subset_strategy: stratified
+  eval_subset_stratify_columns:
+  - model_id
+  - target_score
+  train_sampling_strategy: random
+  length_column_name: length
+  logging_steps: 10
+  eval_steps: 500
+  save_steps: 500
+  save_total_limit: 10
+  seed: 42
+  resume_from_checkpoint: null
+  eval_subset_seed: 42
+  max_grad_norm: 1.0
+distributed:
+  enabled: true
+  strategy: ddp
+  backend: nccl
+  mixed_precision: bf16
+  gradient_checkpointing: false
+  find_unused_parameters: false
+  fsdp:
+    sharding_strategy: full_shard
+    transformer_layer_cls_to_wrap: null
+    activation_checkpointing: true
+    use_orig_params: true
+  deepspeed:
+    zero_stage: 2
+    offload_optimizer_device: none
+    offload_param_device: none
+    stage3_gather_16bit_weights_on_model_save: true
+    gradient_clipping: auto
+    config_overrides: {}
+inference:
+  allowed_scores:
+  - '1'
+  - '2'
+  - '3'
+  - '4'
+  - '5'
+  binary_threshold: 3
+  method: restricted_continuation_logprobs_fast
+  generation_fallback: false
+  batch_size: 64
+  require_adapter: false
+  allow_base_model: true
+evaluation:
+  length_buckets:
+  - 0
+  - 256
+  - 512
+  - 1024
+  - 2048
+  - 3072
+  - 4096
+  - 1000000000
+hub:
+  repo_id: null
+  private: false
+  commit_message: Upload ADeLe distilled judge
+  local_checkpoint_dir: null
+  output_staging_dir: null
+  create_pr: false
+  max_shard_size: 5GB