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_v4
 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: 768
+- Max sequence length: 512
 - Epochs: 1
-- Learning rate: 5e-04
+- Learning rate: 1e-04
 - 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_v4
 
 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

@@ -22,7 +22,7 @@
   "loftq_config": {},
   "lora_alpha": 128,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "down_proj",
-    "q_proj",
     "v_proj",
     "up_proj",
-    "k_proj"
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a8e4809816535505832ffeb01a349eb4090eee7d57964b961531769444e70d
+oid sha256:92deb5e65af1755813d657bd6d24680855b341cb1dd58cfd74b6e54d5c5fbad8
 size 528550256