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
+- hybrid_dataset_v6.jsonl
 language:
 - en
 license: apache-2.0
@@ -15,7 +15,7 @@ tags:
 - dbbench
 ---
 
-# No.19 advanced competition qwen3-4b-agent-trajectory-lora LR=3.5e-6 epoc=3 Counting: 4.0 A100
+# No.20 advanced competition qwen3-4b-agent-trajectory-lora dataset1 LR=3.5e-6 epoc=3 Counting: 4.0 A100
 
 This repository provides a **LoRA adapter** fine-tuned from
 **Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
@@ -62,7 +62,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: u-10bei/dbbench_sft_dataset_react_v4
+Training data: hybrid_dataset_v6.jsonl
 
 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 sha256:8e6a9f9001f738760fe97228bda3b3e3ffa688e2513288da0676b32148302616
+oid sha256:328b8646e93e76fd6499449e8287fc1f2b9b1264b1fe40b6526eae09fbd5fdb5
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7dbb7cad89fc1ab90a24459fd134526dc97b2f535c9c98ab1275a0580e38995
+oid sha256:b164860a42939c193ad43ea59762f45bdc3faa11549ef42eb22d5a52703a0ba7
 size 3077766632