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

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: Qwen/Qwen3-4B-Instruct-2507
 datasets:
-- u-10bei/dbbench_sft_dataset_react_v4
+- u-10bei/sft_alfworld_trajectory_dataset_v5
 language:
 - en
 license: apache-2.0
@@ -14,6 +14,9 @@ tags:
 - alfworld
 - dbbench
 ---
+
+# ＜【課題】ここは自分で記入して下さい＞
+
 This repository provides a **LoRA adapter** fine-tuned from
 **Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
 
@@ -33,9 +36,9 @@ tool use, and recovery from errors.
 
 - Base model: Qwen/Qwen3-4B-Instruct-2507
 - Method: LoRA (full precision base)
-- Max sequence length: 8192
+- Max sequence length: 8184
 - Epochs: 2
-- Learning rate: 1e-06
+- Learning rate: 1e-05
 - LoRA: r=64, alpha=128
 
 ## Usage
@@ -59,7 +62,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: u-10bei/dbbench_sft_dataset_react_v4
+Training data: u-10bei/sft_alfworld_trajectory_dataset_v5
 
 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.

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915460d174261b07c02cde5c472face0b8a6c862cc4da7e932518927e46b9b90
+oid sha256:65021d8df9e20112911792445a51df55552a6c78c291a13d3a36cc17b3c0ad07
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac1132c1e598a60b035bec7f21f480a1d42b2609b551fd28b3162b16003d842
+oid sha256:12d7d21468897595da5f1c259789ce3b237ecbd0642d7c11243decd727a67031
 size 3077766632