Upload LoRA adapter (README written by author)

README.md

@@ -34,8 +34,8 @@ 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
+- Epochs: 2
+- Learning rate: 1e-04
 - LoRA: r=64, alpha=128
 
 ## Usage
@@ -46,7 +46,7 @@ from peft import PeftModel
 import torch
 
 base = "Qwen/Qwen3-4B-Instruct-2507"
-adapter = "your_id/your-repo"
+adapter = "ykuniteke/self-test"
 
 tokenizer = AutoTokenizer.from_pretrained(base)
 model = AutoModelForCausalLM.from_pretrained(

adapter_config.json

@@ -34,12 +34,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "v_proj",
-    "down_proj",
-    "k_proj",
+    "gate_proj",
     "o_proj",
     "up_proj",
-    "gate_proj"
+    "v_proj",
+    "down_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261118305dfb95cb43af266e839475bbbba0a233973f59b85ac7f1b4458af4d7
+oid sha256:03c63f0559157a8376ecf7fa574a63c85444ed7a1a89d80eed4ca4f0138b0d2f
 size 528550256