Create App1.py

App1.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+MODEL_ID = "goonsai-com/civitaiprompts"
+MODEL_VARIANT = "Q4_K_M"  # The quantized version
+
+print("Loading model...")
+tokenizer = AutoTokenizer.from_pretrained(f"hf.co/{MODEL_ID}:{MODEL_VARIANT}")
+model = AutoModelForCausalLM.from_pretrained(
+    f"hf.co/{MODEL_ID}:{MODEL_VARIANT}",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def chat(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    output = model.generate(
+        **inputs,
+        max_length=200,
+        temperature=0.7,
+        do_sample=True
+    )
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+iface = gr.Interface(
+    fn=chat,
+    inputs="text",
+    outputs="text",
+    title="CivitaI Prompt Model",
+    description="Type a prompt and get a response."
+)
+
+iface.launch(server_name="0.0.0.0", server_port=7860)