Upload folder using huggingface_hub

app.py

@@ -0,0 +1,58 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load model
+print("Loading text generation model...")
+model_id = "Yehia-Elsawy/smollm-360m-stories-mlx"
+
+try:
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id)
+    print("✅ Model loaded!")
+except Exception as e:
+    print(f"❌ Error loading model: {e}")
+    raise e
+
+def generate_story(prompt, max_length=200, temperature=0.8):
+    """Generate story continuation from a prompt."""
+    
+    inputs = tokenizer(prompt, return_tensors="pt")
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_length,
+            do_sample=True,
+            temperature=temperature,
+            top_p=0.9,
+            repetition_penalty=1.1
+        )
+    
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return generated_text
+
+# Create interface
+demo = gr.Interface(
+    fn=generate_story,
+    inputs=[
+        gr.Textbox(
+            lines=3, 
+            placeholder="Once upon a time...", 
+            label="Start your story"
+        ),
+        gr.Slider(50, 300, value=150, step=10, label="Length"),
+        gr.Slider(0.5, 1.5, value=0.9, step=0.1, label="Creativity (Temperature)")
+    ],
+    outputs=gr.Textbox(label="Generated Story", lines=10),
+    title="SmolLM Storyteller",
+    description="Fine-tuned on 200k stories. Give it a prompt and watch it continue your tale!",
+    examples=[
+        ["Once upon a time, there was a brave little robot who", 150, 0.9],
+        ["The dragon lived in a cave made of ice.", 150, 0.9],
+        ["My best friend's name is Luna. She loves to", 150, 0.9]
+    ]
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+transformers>=4.40.0
+torch
+gradio
+accelerate
+protobuf
+sentencepiece