Upload folder using huggingface_hub

README.md

@@ -1,37 +1,68 @@
-LoRA adapter Repo ID: Mani124124/structeval-lora
-Base model ID used for training: unsloth/Qwen3-4B-Instruct-2507
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/structured_data_with_cot_dataset_512_v5
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-4B-Instruct-2507
+- lora
+- transformers
+---
 
-This repository provides a LoRA adapter fine-tuned from unsloth/Qwen3-4B-Instruct-2507.
+＜【課題】ここは自分で記入して下さい＞
 
-This repository contains LoRA adapter weights only. The base model must be loaded separately.
+This repository provides a **LoRA adapter** fine-tuned from
+**unsloth/Qwen3-4B-Instruct-2507** using **QLoRA (4-bit, Unsloth)**.
+
+This repository contains **LoRA adapter weights only**.
+The base model must be loaded separately.
 
 ## Training Objective
-This adapter is trained to improve structured output accuracy (JSON / YAML / XML / TOML / CSV).
+
+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.
 
 ## Training Configuration
-Base model: unsloth/Qwen3-4B-Instruct-2507
-Method: LoRA (PEFT)
-Max sequence length: 256
-Epochs: 1
-Learning rate: 5e-05
-LoRA: r=16, alpha=32
+
+- Base model: unsloth/Qwen3-4B-Instruct-2507
+- Method: QLoRA (4-bit)
+- Max sequence length: 256
+- Epochs: 1
+- Learning rate: 5e-05
+- LoRA: r=16, alpha=32
 
 ## Usage
+
+```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 import torch
 
 base = "unsloth/Qwen3-4B-Instruct-2507"
-adapter = "Mani124124/structeval-lora"
+adapter = "your_id/your-repo"
 
-tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(base)
 model = AutoModelForCausalLM.from_pretrained(
     base,
     torch_dtype=torch.float16,
     device_map="auto",
-    trust_remote_code=True,
 )
 model = PeftModel.from_pretrained(model, adapter)
+```
 
 ## Sources & Terms (IMPORTANT)
+
 Training data: u-10bei/structured_data_with_cot_dataset_512_v5
+
+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.
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "q_proj",
     "v_proj",
-    "gate_proj",
     "up_proj",
-    "down_proj"
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

chat_template.jinja

@@ -14,6 +14,14 @@
         {{- '<|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 %}
@@ -23,7 +31,24 @@
     {%- 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" %}
-        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- 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) %}