Upload LoRA adapter (README written by author)

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: Qwen/Qwen3-4B-Instruct-2507
 datasets:
-- daichira/structured-5k-mix-sft
+- daichira/structured-3k-mix-sft
 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: 1024
-- Epochs: 2
-- Learning rate: 1e-05
+- Max sequence length: 768
+- Epochs: 1
+- Learning rate: 2e-04
 - LoRA: r=64, alpha=128
 
 ## Usage
@@ -59,7 +59,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: daichira/structured-5k-mix-sft
+Training data: daichira/structured-3k-mix-sft
 
 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": 0.0,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
-    "o_proj",
-    "v_proj",
     "k_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
     "gate_proj",
-    "up_proj"
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d57fba50d34504c4ba1594b907d44ad550cf0695d37924608521f329f45f5e
+oid sha256:8b1d838308ce48b2eb25b0831161ae5b153dad3595c5a9ad8e367915292f53d4
 size 528550256