Upload merged model (base + LoRA adapter)

README.md

@@ -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: 512
+- Max sequence length: 2048
 - Epochs: 2
-- Learning rate: 1e-06
+- Learning rate: 1e-05
 - 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 = "amu870/test-v0"
 
 tokenizer = AutoTokenizer.from_pretrained(base)
 model = AutoModelForCausalLM.from_pretrained(

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f657cfccd058adf62366939f31e3755f770e34ec4244740b1e40d3e6d76bf7
+oid sha256:71a2762f4667b3098a53b2be1bcdd71f88a683c037c26acc1ab28c217f04e54d
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c902789a01181e391a968a6c63215b27f415864274c73437f4575f74250535
+oid sha256:0a1a77367d3fa1f622dbf41b6d47565cb004b8bb0c3d73269673069d71bad777
 size 3077766632