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

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: Qwen/Qwen2.5-7B-Instruct
 datasets:
-- masa9432/dbbench_cleaned_v1
+- masa9432/agentbench_mix_alf3_db1_v1
 language:
 - en
 license: apache-2.0
@@ -36,9 +36,9 @@ tool use, and recovery from errors.
 
 - Base model: Qwen/Qwen2.5-7B-Instruct
 - Method: LoRA (full precision base)
-- Max sequence length: 2048
+- Max sequence length: 4096
 - Epochs: 2
-- Learning rate: 5e-05
+- Learning rate: 2e-05
 - LoRA: r=16, alpha=32
 
 ## Usage
@@ -62,7 +62,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: masa9432/dbbench_cleaned_v1
+Training data: masa9432/agentbench_mix_alf3_db1_v1
 
 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-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4d34601666cc387a4879c017a87ec2325749cdb4522c27211e34fadf5e1fc7
+oid sha256:c8c9ceda1fab0830c6adc1a808df627be257273ce4463ee852a4e2ad2cf5637f
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbd905e0eed5baef6a67ee6b9660a82e20e2fb371caad3f1acf5b46752a5b5a
+oid sha256:9823e1ae86d760c15378b2b0fb1677612b95d700c542a62a7226aca12f6537c5
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:264b5ddd9a5c81493fa04944303a09acbcddb40221f1efd373654672785a404a
+oid sha256:fb14a5611b99e75b706004051a07242be7972ce9bf3e155486eb89cbc57c75a6
 size 4330865200