Upload folder using huggingface_hub

README.md

@@ -1,65 +1,49 @@
 ---
 base_model: Qwen/Qwen3-4B-Instruct-2507
 datasets:
-- u-10bei/structured_data_with_cot_dataset_512_v2
+- u-10bei/dpo-dataset-qwen-cot
 language:
 - en
 license: apache-2.0
-library_name: peft
+library_name: transformers
 pipeline_tag: text-generation
 tags:
-- qlora
-- lora
-- structured-output
+- dpo
+- unsloth
+- qwen
+- alignment
 ---
 
-# SFT LoRA for Structured Output (Qwen3-4B)
+# DPO-aligned Qwen3-4B for Structured Output
 
-This repository provides a **LoRA adapter** fine-tuned from
-**Qwen/Qwen3-4B-Instruct-2507** using **QLoRA (4-bit, Unsloth)**.
+This model is a fine-tuned version of **Qwen/Qwen3-4B-Instruct-2507** using **Direct Preference Optimization (DPO)** via the **Unsloth** library.
 
-This repository contains **LoRA adapter weights only**.
-The base model must be loaded separately.
+This repository contains the **full-merged 16-bit weights**. No adapter loading is required.
 
 ## Training Objective
-
-This adapter is trained to improve **structured output accuracy**
-(JSON / YAML / XML / TOML / CSV).
-
-Loss is applied only to the final assistant output,
-while intermediate reasoning (Chain-of-Thought) is masked.
+This model has been optimized using DPO to align its responses with preferred outputs, focusing on improving reasoning (Chain-of-Thought) and structured response quality.
 
 ## Training Configuration
-
-- Base model: Qwen/Qwen3-4B-Instruct-2507
-- Method: QLoRA (4-bit)
-- Max sequence length: 1024
-- Epochs: 2
-- Learning rate: 1e-06
-- LoRA: r=64, alpha=128
+- **Base model**: Qwen/Qwen3-4B-Instruct-2507
+- **SFT Adapter**: lora_structeval_t_qwen3_4b (merged before DPO)
+- **Method**: DPO (Direct Preference Optimization)
+- **Epochs**: 1
+- **Learning rate**: 1e-07
+- **Beta**: 0.1
+- **Max sequence length**: 1024
+- **LoRA Config**: r=8, alpha=16 (merged into base)
 
 ## Usage
-
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel
 import torch
 
-base = "Qwen/Qwen3-4B-Instruct-2507"
-adapter = "kentof/sft-qwen3-4b-lora"
-
-tokenizer = AutoTokenizer.from_pretrained(base)
-model = AutoModelForCausalLM.from_pretrained(
-    base,
-    torch_dtype=torch.float16,
-    device_map="auto",
-)
-model = PeftModel.from_pretrained(model, adapter)
+model_id = "kentof/dpo-qwen-cot-merged"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
 ```
 
-## Sources & Terms (IMPORTANT)
-
-Training data: u-10bei/structured_data_with_cot_dataset_512_v2
-
-Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
-Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
+## Sources & License (IMPORTANT)
+* **Training Data**: generate/data/data_dpo.json
+* **License**: MIT License.
+* **Compliance**: Users must follow the original base model's license terms.

adapter_config.json

@@ -5,7 +5,7 @@
     "parent_library": "transformers.models.qwen3.modeling_qwen3",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
+    "q_proj",
     "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
     "v_proj",
-    "q_proj",
-    "up_proj",
-    "k_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e5c96c49ab57f8c0bc1a3906b42981984b3cbd8035c7c9c8c9182832407444
+oid sha256:53cf1c8bc09d85b5536d70eb7786f9c4742a9eb2a2aa84c1381083846bdec6f2
 size 528550256

chat_template.jinja

@@ -1,80 +1,47 @@
 {%- if tools %}
     {{- '<|im_start|>system\n' }}
-    {%- if messages[0].role == 'system' %}
-        {{- messages[0].content + '\n\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
     {%- 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>" }}
+    {{- "\n\n# 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' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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' }}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.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 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
         {%- 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 }}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
             {%- 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 %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
         {{- '<|im_end|>\n' }}
     {%- elif message.role == "tool" %}
-        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-            {{- '<|im_start|>user' }}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}            {{- '<|im_start|>user' }}
         {%- endif %}
         {{- '\n<tool_response>\n' }}
-        {{- content }}
+        {{- message.content }}
         {{- '\n</tool_response>' }}
         {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
             {{- '<|im_end|>\n' }}
@@ -83,4 +50,4 @@
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
-{%- endif %}
+{%- endif %}

tokenizer_config.json

@@ -233,7 +233,7 @@
   "extra_special_tokens": {},
   "model_max_length": 262144,
   "pad_token": "<|vision_pad|>",
-  "padding_side": "right",
+  "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce087cbc9637eff2c7d6cb16f84b3dd9cfc89ef4b4d609541a720a38afa12a3b
+size 6801