Upload LoRA adapter (README written by author)

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: Qwen/Qwen3-4B-Instruct-2507
 datasets:
-- u-10bei/structured_data_with_cot_dataset_512_v2
+- u-10bei/structured_data_with_cot_dataset_512_v5
 language:
 - en
 license: apache-2.0
@@ -33,9 +33,9 @@ while intermediate reasoning (Chain-of-Thought) is masked.
 
 - Base model: Qwen/Qwen3-4B-Instruct-2507
 - Method: QLoRA (4-bit)
-- Max sequence length: 512
-- Epochs: 1
-- Learning rate: 1e-06
+- Max sequence length: 1024
+- Epochs: 2
+- Learning rate: 2e-05
 - LoRA: r=64, alpha=128
 
 ## Usage
@@ -59,7 +59,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: u-10bei/structured_data_with_cot_dataset_512_v2
+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.

adapter_config.json

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
     "up_proj",
-    "k_proj",
+    "down_proj",
     "v_proj",
+    "k_proj",
     "q_proj",
-    "gate_proj"
+    "gate_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c8646a715852f02cd88285bceb26f2404f23b43a1967ca5bca631451b9a69e
+oid sha256:78b54253804503774ad15e22b4f28b1f4aff6f04e5ae4d06067990a27ee7f5ae
 size 528550256