Upload LoRA adapter (README written by author)

README.md

@@ -34,9 +34,9 @@ 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
-- LoRA: r=64, alpha=128
+- Epochs: 3
+- Learning rate: 1e-04
+- LoRA: r=96, alpha=128
 
 ## Usage
 

adapter_config.json

@@ -29,17 +29,17 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 96,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "v_proj",
     "q_proj",
-    "down_proj",
+    "k_proj",
     "up_proj",
-    "o_proj",
-    "k_proj"
+    "down_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 sha256:03ff6778879a8770fc4f06014fc6c7b8ab58fb0e2e0581f5d39c060ac20b06df
-size 528550256
+oid sha256:56c09a130e71459bff559aa2f9bd646725c2c7608b191e9208c918dc02680e28
+size 792791480