Upload merged model with correct dataset metadata

README.md

@@ -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
+- Max sequence length: 4096
+- Epochs: 3
 - Learning rate: 1e-05
 - LoRA: r=64, alpha=128
 
@@ -63,7 +63,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: u-10bei/dbbench_sft_dataset_react_v4
+Training data: u-10bei/dbbench_sft_dataset_react_v3
 
 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 sha256:41c8ffdcb57d47e1cd637bbe41bff42690598a3a47a01b0aaa794509ab8672b4
+oid sha256:169b09d135f3a2b1876893e3f47106b66c74d0fd6e08ab28f63c5f4e240d33a8
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a88f84e7c99c50cbfd017a040d75c2d4eacf359fe3df882886e635e0cb3616
+oid sha256:b37b6138965b17194d2308c5870ff8d06f6b0766b53702b8b97c110bfbbf219a
 size 3077766632