Initial LoRA adapter upload

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,118 @@
+---
+library_name: peft
+license: cc-by-nc-4.0
+language:
+  - en
+tags:
+  - peft
+  - safetensors
+  - lora
+  - complexity-classification
+  - llm-routing
+  - query-difficulty
+  - brick
+  - text-classification
+  - semantic-router
+  - inference-optimization
+  - cost-reduction
+  - reasoning-budget
+base_model: Qwen/Qwen3.5-0.8B
+pipeline_tag: text-classification
+model-index:
+  - name: brick-complexity-2-eco
+    results:
+      - task:
+          type: text-classification
+          name: Query Complexity Classification
+        dataset:
+          name: MMLU-Pro labeled 2K benchmark
+          type: regolo/brick-mmlu-pro-2k
+          split: test
+        metrics:
+          - type: accuracy
+            value: 0.7277
+            name: Accuracy (3-class)
+          - type: f1
+            value: 0.4246
+            name: Macro F1
+---
+
+<div align="center">
+
+# Brick Complexity Classifier v2 — `eco`
+
+### Efficient variant trained on 9K empirical-consensus labels (Qwen3.5-9B + 3.5-122B + MiniMax-M2.5 agreement on MMLU-Pro).
+
+**[Regolo.ai](https://regolo.ai) | [Brick SR1 on GitHub](https://github.com/regolo-ai/brick-SR1)**
+
+[![License: CC BY-NC 4.0](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc/4.0/)
+[![Base Model](https://img.shields.io/badge/Base-Qwen3.5--0.8B-blue)](https://huggingface.co/Qwen/Qwen3.5-0.8B)
+
+</div>
+
+---
+
+## Model Details
+
+| Property | Value |
+|---|---|
+| **Variant** | `eco` |
+| **Base model** | [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) |
+| **Adapter type** | LoRA (r=32, α=32, dropout=0.1) |
+| **Training source** | Empirical 3-model consensus on 12K MMLU-Pro full benchmark |
+| **Training examples** | 9K |
+| **Output classes** | 3 (`easy`, `medium`, `hard`) |
+| **Loss** | Asymmetric cross-entropy (over_lambda=0.7, label_smoothing=0.08) |
+| **License** | CC BY-NC 4.0 |
+
+## Benchmark (MMLU-Pro labeled 2K)
+
+| Metric | Value |
+|---|---:|
+| Accuracy (3-class) | 72.77% |
+| Macro F1 | 0.4246 |
+| Overestimate rate | 7.77% |
+| Underestimate rate | 19.46% |
+
+## Family Members
+
+| Variant | Target | Accuracy | Macro F1 |
+|---|---|---:|---:|
+| [brick-complexity-2-eco](https://huggingface.co/regolo/brick-complexity-2-eco) | Cost savings | 72.77% | 0.4246 |
+| [brick-complexity-2-max](https://huggingface.co/regolo/brick-complexity-2-max) | Max accuracy | 77.16% | 0.7707 |
+
+## Available Formats
+
+| Format | Link |
+|---|---|
+| LoRA adapter | [regolo/brick-complexity-2-eco](https://huggingface.co/regolo/brick-complexity-2-eco) |
+| GGUF BF16 | [regolo/brick-complexity-2-eco-BF16-GGUF](https://huggingface.co/regolo/brick-complexity-2-eco-BF16-GGUF) |
+| GGUF Q8_0 | [regolo/brick-complexity-2-eco-Q8_0-GGUF](https://huggingface.co/regolo/brick-complexity-2-eco-Q8_0-GGUF) |
+| GGUF Q4_K_M | [regolo/brick-complexity-2-eco-Q4_K_M-GGUF](https://huggingface.co/regolo/brick-complexity-2-eco-Q4_K_M-GGUF) |
+
+## Usage (PEFT)
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-0.8B", torch_dtype=torch.bfloat16)
+tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-0.8B")
+model = PeftModel.from_pretrained(base, "regolo/brick-complexity-2-eco").eval()
+
+system = """You are a query difficulty classifier for an LLM routing system.
+Classify each query as easy, medium, or hard based on the cognitive depth and domain expertise required to answer correctly.
+Respond with ONLY one word: easy, medium, or hard."""
+prompt = f"<|im_start|>system\n{system}<|im_end|>\n<|im_start|>user\nClassify: Design a distributed consensus algorithm<|im_end|>\n<|im_start|>assistant\n"
+ids = tok(prompt, return_tensors="pt").input_ids
+out = model.generate(ids, max_new_tokens=3, do_sample=False)
+print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True).strip())
+# Output: hard
+```
+
+## About Brick
+
+[Regolo.ai](https://regolo.ai) is the EU-sovereign LLM inference platform built on [Seeweb](https://www.seeweb.it/) infrastructure. **Brick** is our open-source semantic routing system that intelligently distributes queries across model pools, optimizing for cost, latency, and quality.
+
+**[Website](https://regolo.ai) | [Docs](https://docs.regolo.ai) | [GitHub](https://github.com/regolo-ai) | [Discord](https://discord.gg/myuuVFcfJw)**

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/Qwen3.5-0.8B",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "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": [
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f110ce6f158bce6af9c3ab0dfb8c64dffb89954d96afeb8eb3ec4be6fdb33908
+size 51143344

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9701f3f476eb8b5de4b88f21b937e7d0089156a143646261758b82d9200cd95
+size 19989621

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

training_metadata.json

@@ -0,0 +1,28 @@
+{
+  "config": {
+    "base": "Qwen/Qwen3.5-0.8B",
+    "train": "/data/dataset/empirical_train.jsonl",
+    "val": "/data/dataset/empirical_val.jsonl",
+    "test": "/data/dataset/empirical_test.jsonl",
+    "output": "/data/output/qwen35-empirical-asym-lora",
+    "epochs": 3,
+    "batch_size": 16,
+    "lr": "1e-4",
+    "max_length": 768,
+    "lora_r": 32,
+    "lora_alpha": 32,
+    "lora_dropout": 0.1,
+    "over_lambda": 0.7,
+    "label_smoothing": 0.08,
+    "eval_steps": 200
+  },
+  "training_time_s": 2338.5,
+  "system_prompt": "PRODUCTION (for Brick drop-in compatibility)",
+  "test": {
+    "n": 1994,
+    "accuracy": 0.7276830491474423,
+    "over_rate": 0.07773319959879639,
+    "under_rate": 0.1945837512537613,
+    "macro_f1": 0.42460581599084596
+  }
+}