Upload merged Qwen2.5-7B-Instruct model (auto-generated README)

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: Qwen/Qwen2.5-7B-Instruct
 datasets:
-- alfworld_v5_filtered.jsonl
+- alfworld_v5_filtered_023.jsonl
 language:
 - en
 license: apache-2.0
@@ -36,8 +36,7 @@ tool use, and recovery from errors.
 
 To improve the reasoning efficiency and reduce the risk of infinite loops (repetitive actions), the training dataset was customized with the following filtering strategy:
 
-- **Optimization of Exploration**: Trajectories with **9 or more "detours"** were excluded from the training set.
-- **Robustness Maintenance**: Trajectories with **0 to 8 detours** were retained.
+- **Robustness Maintenance**: Trajectories with **0, 2, 3 detours** were retained.
 
 ## Training Configuration
 
@@ -69,7 +68,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: alfworld_v5_filtered.jsonl
+Training data: alfworld_v5_filtered_023.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-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e20937a830b04addef6f19c1e1a998f392b8d6e2e35efd8332ff5c2c36d568
+oid sha256:264b8594d771d2fda5a6529ed7124e5b774dae17c439e938783056d72f81a158
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fd090f9fd3988b30ebd46fba06b9d0dacf5110a93107dd1e494fae458df2397
+oid sha256:142033e5a8a2521642588db5dac1748666157cca68055514dd4e842b416eaee7
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de2d708b0d907f2d2c0dab391009c7122a9e7d9504b85e0987fd3ac5c0c1d24
+oid sha256:7556cc2d371566debf80ad3d7e1f91054f8bede84443403a8f0bc86d6fae8a40
 size 4330865200