Upload folder using huggingface_hub

.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 +1,92 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+base_model: Qwen/Qwen3-1.7B
+tags:
+- agent
+- tool-use
+- distillation
+- math
+- code
+- reasoning
+pipeline_tag: text-generation
+---
+
+<div align="center">
+
+<h1>SOD-1.7B</h1>
+
+<p>
+  <a href="https://arxiv.org/abs/2605.07725">
+    <img src="https://img.shields.io/badge/Paper-Arxiv-red?logo=arxiv&logoColor=red" alt="Paper on arXiv"/>
+  </a>
+  <a href="https://github.com/YoungZ365/SOD">
+    <img src="https://img.shields.io/badge/Code-GitHub-black?logo=github&logoColor=white" alt="Code on GitHub"/>
+  </a>
+</p>
+
+</div>
+
+## About
+
+**SOD-1.7B** is a 1.7B student model distilled from a 4B teacher using **SOD (Step-wise On-policy Distillation)**, a method designed for training small language model agents with tool-integrated reasoning capabilities.
+
+SOD addresses the **cascading error propagation** problem in on-policy distillation for agentic reasoning by introducing an adaptive step-level weighting mechanism that suppresses distillation loss on drifted steps and restores supervision when the student recovers alignment — all at negligible additional computational cost.
+
+## Model Information
+
+| Attribute | Value |
+|-----------|-------|
+| Base Model | [Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) |
+| Teacher Model | [SOD-GRPO_teacher-4B](https://huggingface.co/youngzhong/SOD-GRPO_teacher-4B) |
+| Training Pipeline | Cold-Start SFT → SOD (Step-wise On-policy Distillation) |
+| Parameters | 1.7B |
+
+## Related Models
+
+| Model | Description |
+|-------|-------------|
+| [SOD-0.6B](https://huggingface.co/youngzhong/SOD-0.6B) | SOD-distilled 0.6B student |
+| [SOD-1.7B](https://huggingface.co/youngzhong/SOD-1.7B) | SOD-distilled 1.7B student (this model) |
+| [SOD-GRPO_teacher-4B](https://huggingface.co/youngzhong/SOD-GRPO_teacher-4B) | GRPO-trained 4B teacher model |
+
+## Performance
+
+We report **average@32** over 5 runs on challenging math, science, and code benchmarks.
+
+### 1.7B Student Results
+
+| Method | AIME 2024 | AIME 2025 | GPQA-Diamond | LiveCodeBench-v6 | Average |
+|--------|-----------|-----------|--------------|------------------|---------|
+| Vanilla | 9.90 | 8.96 | 26.80 | 22.73 | 17.10 |
+| SFT | 26.77 | 22.40 | 29.85 | 24.63 | 25.91 |
+| GRPO | 25.63 | 21.67 | 33.55 | 20.70 | 25.39 |
+| OPD | 43.86 | 37.04 | 31.73 | 32.45 | 36.27 |
+| OPSD_gt | 33.85 | 24.69 | 35.02 | 22.73 | 29.07 |
+| OPSD_hint | 34.42 | 21.43 | 33.46 | 23.12 | 28.11 |
+| **SOD (This Model)** | **50.83** | **41.72** | **38.72** | **40.63** | **42.98** |
+
+### Teacher Model (4B)
+
+| Method | AIME 2024 | AIME 2025 | GPQA-Diamond | LiveCodeBench-v6 | Average |
+|--------|-----------|-----------|--------------|------------------|---------|
+| GRPO | 67.60 | 60.42 | 55.19 | 63.13 | 61.59 |
+
+## Key Highlights
+
+- 🏆 **Recovers 69.8% of teacher performance** with only 1.7B parameters (42.98 vs 61.59)
+- 📈 **+18.5% over second-best baseline** (OPD) on average
+- 💡 **Minimal extra compute**: The divergence metric reuses log-probabilities already computed in the forward pass
+
+## Citation
+
+```bibtex
+@article{zhong2026sod,
+      title={SOD: Step-wise On-policy Distillation for Small Language Model Agents}, 
+      author={Qiyong Zhong and Mao Zheng and Mingyang Song and Xin Lin and Jie Sun and Houcheng Jiang and Xiang Wang and Junfeng Fang},
+      journal={arXiv preprint arXiv:2605.07725},
+      year={2026}
+}
+```

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 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.4.0",
+  "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": "5.4.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab51265b01ba5034fdf13b455823b8ae32fc051772dfc8c4c44aaf06e4307db
+size 4063515640

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

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
+}