Edit gitignore and huggingface space.py

.github/workflows/huggingface.yml

@@ -0,0 +1,42 @@
+name: Uploading on Huggingface
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Set Git identity
+        run: |
+          git config --global user.email "[email protected]"
+          git config --global user.name "GitHub Actions"
+
+      - name: Update README.md
+        run: |
+          tmp_file=$(mktemp)
+          echo "---" >> $tmp_file
+          echo "title: Burmese GPT" >> $tmp_file
+          echo "emoji: 💫️" >> $tmp_file
+          echo "colorFrom: yellow" >> $tmp_file
+          echo "colorTo: blue" >> $tmp_file
+          echo "sdk: streamlit" >> $tmp_file
+          echo "sdk_version: 1.29.0" >> $tmp_file
+          echo "app_file: space.py" >> $tmp_file
+          echo "pinned: false" >> $tmp_file
+          echo "license: openrail" >> $tmp_file
+          echo "---" >> $tmp_file
+          echo "" >> $tmp_file
+          cat README.md >> $tmp_file
+          mv $tmp_file README.md
+          git add README.md
+          git commit -m "Updated README.md"
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://zaibutcooler:[email protected]/spaces/zaibutcooler/burmese-gpt --force main

.gitignore

@@ -139,4 +139,6 @@ cython_debug/
 # Logs
 *.log
 
-.idea
+.idea
+
+checkpoints/

space.py

@@ -3,6 +3,8 @@ from transformers import AutoTokenizer
 import streamlit as st
 from burmese_gpt.config import ModelConfig
 from burmese_gpt.models import BurmeseGPT
+from .scripts.download import download_pretrained_model
+import os
 
 # Model configuration
 VOCAB_SIZE = 119547
@@ -12,6 +14,13 @@ CHECKPOINT_PATH = "checkpoints/best_model.pth"
 # Load model function (cached to avoid reloading on every interaction)
 @st.cache_resource
 def load_model():
+    if os.path.exists(CHECKPOINT_PATH):
+        st.warning("Model already exists, skipping download.")
+    else:
+        st.info("Downloading model...")
+        download_pretrained_model()
+        st.success("Model downloaded successfully.")
+
     model_config = ModelConfig()
 
     tokenizer = AutoTokenizer.from_pretrained("bert-base-multilingual-cased")