Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)

README.md

@@ -15,7 +15,7 @@ tags:
 - dbbench
 ---
 
-# ＜【課題】ここは自分で記入して下さい＞
+# ＜qwen3-4b-agent-trajectory-lora＞
 
 This repository provides a **LoRA adapter** fine-tuned from
 **Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
@@ -37,8 +37,8 @@ tool use, and recovery from errors.
 - Base model: Qwen/Qwen3-4B-Instruct-2507
 - Method: LoRA (full precision base)
 - Max sequence length: 2048
-- Epochs: 2
-- Learning rate: 2e-06
+- Epochs: 3
+- Learning rate: 1e-04
 - LoRA: r=64, alpha=128
 
 ## Usage

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f32d522808df4718dc6dcfc1497ed582a044aa3ffcccb7f3b4751de64c5d108
+oid sha256:3712f492f085a2029db752b20cc19670c19260b6a9735b01a4503769e2970784
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ba07b41cbbd6a3de3d8947a107ad8492325a421e8420b8573aeedec3003a3f
+oid sha256:b6a3bc69009d5a468e4149e071e51d7840420f15f83499a53fae6440164ca028
 size 3077766632