Create app.py

app.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+# Your Hugging Face model repo ID
+model_id = "chanystrange/mistral-agri-merged_143"
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    load_in_4bit=True
+)
+
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+# Function for API
+def chat(prompt):
+    output = generator(prompt, max_new_tokens=200, do_sample=True)
+    return output[0]["generated_text"]
+
+# Gradio Interface (this works as REST API too)
+demo = gr.Interface(fn=chat, inputs="text", outputs="text")
+
+# Launch Space with share=True to get a public URL
+demo.launch(server_name="0.0.0.0", server_port=7860, share=True)