Initial upload: R14 (chain endpoint, 7-domain MCQ) + model card

.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 +1,178 @@
+---
+license: apache-2.0
+language:
+- en
+- kk
+base_model:
+- Qwen/Qwen3-0.6B
+pipeline_tag: text-generation
+tags:
+- edge-cloud-routing
+- verbalized-confidence
+- self-aware
+- routing
+- continual-learning
+- multi-round
+library_name: transformers
+---
+
+# FogGen: Self-Aware Edge–Cloud LLM Router
+
+> **A 0.6B parameter edge LLM trained to emit a calibrated verbalized confidence score before its answer, enabling efficient edge–cloud routing without an external router.**
+
+FogGen is a small, self-aware edge model that knows when to answer locally and when to defer to a stronger cloud model. The model emits a discrete confidence score (one of `0.0, 0.25, 0.5, 0.75, 1.0`) before producing its answer, and a routing threshold `τ` decides whether to keep the local answer or escalate to the cloud.
+
+The released checkpoint is the endpoint (`R14`) of a 14-round continual-learning chain that trained the model across seven domains: finance, science, coding, law, math, Kazakh culture, and medicine.
+
+## Quick demo
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model = AutoModelForCausalLM.from_pretrained("issai/foggen", torch_dtype="bfloat16", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("issai/foggen")
+
+SYSTEM = """You are a self-aware multiple-choice assistant.
+
+Rules:
+- Do not output <think> tags.
+- First, assess your confidence in solving this question.
+- Then give your answer.
+- Output format:
+  Confidence: <0.0|0.25|0.5|0.75|1.0>
+  Final answer: <OPTION_LETTER>"""
+
+question = """A firm reports $400M in total liabilities and $600M in shareholders' equity.
+What is the firm's debt-to-equity ratio?
+
+A. 0.67
+B. 1.00
+C. 1.50
+D. 2.00"""
+
+messages = [
+    {"role": "system", "content": SYSTEM},
+    {"role": "user", "content": question},
+]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True,
+                                       enable_thinking=False).to(model.device)
+outputs = model.generate(inputs, max_new_tokens=64, do_sample=False)
+print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
+# Expected:
+#   Confidence: 1.0
+#   Final answer: A
+```
+
+## How routing works
+
+```python
+import re
+
+def route_query(model_output: str, tau: float = 0.5):
+    """Parse FogGen output. Returns (action, confidence, answer).
+    action is 'keep_local' if confidence >= tau, else 'route_to_cloud'."""
+    conf_match = re.search(r"Confidence\s*:\s*([\d.]+)", model_output)
+    ans_match  = re.search(r"Final\s+answer\s*:\s*([A-D])", model_output)
+    if not conf_match: return "route_to_cloud", None, None
+    confidence = float(conf_match.group(1))
+    answer = ans_match.group(1) if ans_match else None
+    return ("keep_local" if confidence >= tau else "route_to_cloud", confidence, answer)
+```
+
+At τ=0.5 on the trained domains, the model routes ~22% of queries to the cloud while achieving 67.8% mean system accuracy.
+
+## Model details
+
+| | |
+|---|---|
+| **Base model** | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) |
+| **Parameters** | 0.6 B |
+| **Training method** | LoRA SFT (rank=16, α=32, all-linear), bf16, 2 epochs/round |
+| **Rounds** | 14 sequential rounds (R0 → R14) |
+| **Training tokens** | ~1800 SFT rows × 14 rounds |
+| **Domains** | finance, science, coding, law, math, Kazakh culture, medical |
+| **Cloud teacher** | [Qwen3-30B-A3B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507) |
+| **Output format** | `Confidence: <bucket>\nFinal answer: <letter>` |
+| **Confidence buckets** | 5 discrete values: 0.0, 0.25, 0.5, 0.75, 1.0 |
+| **License** | Apache 2.0 (inherited from base) |
+
+## Performance
+
+System accuracy at τ=0.5 on seven MCQ domains (full test sets, ~16,200 questions), measured against Random routing and a cloud-only baseline (Qwen3-30B-A3B-Instruct-2507):
+
+| Domain | Cloud only | R14 raw | Random @ τ=0.5 | **FogGen @ τ=0.5** | Cloud routed |
+|---|---|---|---|---|---|
+| Finance | 69.5% | 57.0% | 59.9% | **65.8%** | 23.3% |
+| Science | 72.7% | 56.9% | 60.1% | **64.5%** | 20.4% |
+| Coding | 74.2% | 61.8% | 64.2% | **69.5%** | 19.7% |
+| Law | 70.7% | 55.3% | 58.4% | **62.4%** | 20.1% |
+| Math | 60.1% | 42.2% | 50.8% | **58.1%** | 47.7% |
+| Kazakh culture | 95.8% | 91.3% | 91.4% | **91.9%** | 1.0% |
+| Medical | 74.0% | 52.6% | 57.1% | **62.2%** | 20.9% |
+| **Mean** | **73.9%** | **59.6%** | **63.1%** | **67.8%** | **21.9%** |
+
+**Routing benefit over Random: +4.6 percentage points mean at τ=0.5.**
+
+### Baseline comparison
+
+Direct comparison against AutoMix (Aggarwal et al., 2024) on the same R14 checkpoint, same evaluation sets:
+
+| Method | SysAcc | Cloud routed | Δ over Random | Fwd passes / query |
+|---|---|---|---|---|
+| AutoMix | 67.2% | 29.0% | +3.7 | 9 (1 answer + 8 verify) |
+| **FogGen (ours)** | **67.8%** | **21.9%** | **+4.6** | **1** |
+
+FogGen achieves higher accuracy at lower cloud cost and 9× lower per-query inference cost.
+
+## Open-ended generalization
+
+The MCQ-trained chain transfers to open-ended task types zero-shot. Local accuracy and routing benefit at τ=0.5 on three held-out OE benchmarks:
+
+| Benchmark | Format | R14 raw | R14 Δ@τ=0.5 |
+|---|---|---|---|
+| [SQuAD v1.1](https://huggingface.co/datasets/rajpurkar/squad) | extractive RC | 81.0% | +1.4 |
+| [TruthfulQA gen](https://huggingface.co/datasets/truthfulqa/truthful_qa) | adversarial factual | 36.5% | −0.7 (anti-calibrated) |
+| [GSM8K](https://huggingface.co/datasets/openai/gsm8k) (CoT) | math word-problems | 52.0% | +2.2 |
+
+One additional round of OE training (R15, 1876 SFT rows) lifts these to +5.5, +3.5, +6.0 pp local accuracy respectively.
+
+## Intended use
+
+- **Edge–cloud routing systems** where a 0.6B model handles routine queries and a stronger cloud model handles harder ones.
+- **Single-pass inference**: the model produces both the answer and the routing signal in one forward pass — no separate verification calls needed.
+- **Calibrated thresholding**: change τ (default 0.5) to trade off local-vs-cloud cost.
+
+### Out-of-scope use
+
+- Standalone production use without a cloud fallback. The model is small and the confidence span is calibrated to signal *when to escalate*, not to produce gold answers on hard queries.
+- Generation tasks beyond what was tested (extractive QA, factual recall, CoT math) without additional task-type training.
+- Reliance on the confidence signal for adversarial-factuality benchmarks like TruthfulQA, where verbalized confidence is anti-calibrated by design of the dataset (see Tian et al., 2023).
+
+## Limitations
+
+- **Adversarial factual benchmarks (TruthfulQA)**: confidence signal is anti-calibrated — the model is confidently wrong on common misconceptions.
+- **MCQ regression after open-ended training**: one round of OE training causes ~1.7 pp mean MCQ regression.
+- **Held-out AC ordering**: when the system prompt is changed from confidence-first (CA) to answer-first (AC), held-out tasks regress ~1.2 pp on routing benefit.
+- **Prompt sensitivity**: the model is trained on a specific FogGen-format prompt. Non-FogGen prompts on the same R14 weights lose 1-10 pp of task accuracy depending on domain.
+
+## Reproducibility
+
+- All training scripts, evaluation pipelines, and per-question outputs are in the paper's reproducibility appendix.
+- The 14-round chain uses LoRA SFT only (no RL), with identical hyperparameters per round.
+- Training framework: [ms-swift](https://github.com/modelscope/ms-swift) with vLLM serving for self-labeling and evaluation.
+
+## Citation
+
+```bibtex
+@article{foggen2026,
+  title={FogGen: A Self-Aware Edge-Cloud LLM Router with Verbalized Confidence Tokens},
+  author={... [author list TBD] ...},
+  journal={Knowledge-Based Systems},
+  year={2026},
+  note={Under review}
+}
+```
+
+## Acknowledgements
+
+Developed at the Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University. Cloud teacher and base model from the Qwen team at Alibaba.

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

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 %}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8e94dc6613d275be39edf768d25110a8c5c4665e52353019f5cd8d19a42064
+size 1192135096

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}