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_v4
+- u-10bei/structured_data_with_cot_dataset_512_v2
 language:
 - en
 license: apache-2.0
@@ -35,8 +35,8 @@ while intermediate reasoning (Chain-of-Thought) is masked.
 - Method: QLoRA (4-bit)
 - Max sequence length: 512
 - Epochs: 1
-- Learning rate: 1e-04
-- LoRA: r=64, alpha=128
+- Learning rate: 1e-05
+- LoRA: r=8, alpha=8
 
 ## Usage
 
@@ -59,7 +59,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: u-10bei/structured_data_with_cot_dataset_512_v4
+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.

adapter_config.json

@@ -20,26 +20,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 8,
   "lora_bias": false,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "k_proj",
-    "o_proj",
     "q_proj",
-    "down_proj",
-    "gate_proj"
+    "v_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 sha256:92deb5e65af1755813d657bd6d24680855b341cb1dd58cfd74b6e54d5c5fbad8
-size 528550256
+oid sha256:b0fcb07840ff61eb0ce85e9951d71f2db573005dbf5fe1019d149e8c28eec882
+size 19492872