Sync from GitHub

.gitattributes

@@ -0,0 +1 @@
+assets/vis.gif filter=lfs diff=lfs merge=lfs -text

.github/workflows/sync_hf.yml

@@ -15,4 +15,15 @@ jobs:
       - name: Push to hub
         env:
           HF_TOKEN: ${{ secrets.HF_TOKEN }}
-        run: git push -f https://nuriyev:$HF_TOKEN@huggingface.co/spaces/nuriyev/text2mcdm HEAD:main
+        run: |
+          pip install huggingface_hub
+          python - <<EOF
+          from huggingface_hub import HfApi
+          api = HfApi()
+          api.upload_folder(
+              folder_path=".",
+              repo_id="nuriyev/text2mcdm",
+              repo_type="space",
+              commit_message="Sync from GitHub",
+          )
+          EOF

.gitignore

@@ -1,6 +1,7 @@
 .*
 !.gitignore
 !.github/
+!.huggingfaceignore
 trash/
 __pycache__/
 outputs/

.huggingfaceignore

@@ -0,0 +1,2 @@
+.vscode/
+assets/vis.gif

README.md

@@ -13,6 +13,10 @@ pinned: false
 
 How do you make decisions when your reasoning is messy and contains uncertainty, subjectivity, or contradictions? This project leverages large language models fine-tuned to extract Z-number decision matrix from natural language narrative. The extracted matrix is then analyzed using z-number-based Multi-Criteria Decision-Making (MCDM) methods (TOPSIS, PROMETHEE).
 
+[![Demo](./assets/vis.gif)](https://huggingface.co/spaces/nuriyev/text2mcdm)
+
+[Demo](https://huggingface.co/spaces/nuriyev/text2mcdm) | [Model](https://huggingface.co/nuriyev/Qwen3-4B-znum-decision-matrix) | [Dataset](https://huggingface.co/datasets/nuriyev/text2mcdm)
+
 ## Usage
 
 ```bash