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_plus_alfworld_v2
+- masa9432/dbbench_x3_plus_alfworld_x1
 language:
 - en
 license: apache-2.0
@@ -37,7 +37,7 @@ tool use, and recovery from errors.
 - Base model: Qwen/Qwen2.5-7B-Instruct
 - Method: LoRA (full precision base)
 - Max sequence length: 4096
-- Epochs: 3
+- Epochs: 1
 - Learning rate: 1e-05
 - LoRA: r=32, alpha=64
 
@@ -62,7 +62,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: masa9432/dbbench_plus_alfworld_v2
+Training data: masa9432/dbbench_x3_plus_alfworld_x1
 
 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:ecdf2388c09d7b797157f100c9477491c710ae6af9590bd8fcbc107b2f457653
+oid sha256:9e3cf5fb737003a8a1992de9ff09fa58984d4de6a09a8c16cd02e5ef6970d410
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bab6b7dec11f546286a7d54261f626307a4e843d9e654e4bcc6583847ecbdfe
+oid sha256:117b055a20794bf6e4c15263ef634ac3eb0a6a376d737e81b81eff903db9163b
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbed48c10c8a2812b1afe61e0e98b970172a3b47d16f2c0a19b27bb3c27ae939
+oid sha256:5d9fd150d1219b94b43bba3c66707fc854f06a85fae3930b3e5cabd9253a82ce
 size 4330865200