Create app.py

app.py

@@ -0,0 +1,17 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_name = "TheBloke/MythoMax-L2-13B-GGUF"  # Change this if you're doing OpenHermes instead
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
+
+def chat(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=200)
+    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return reply
+
+demo = gr.Interface(fn=chat, inputs="text", outputs="text")
+demo.launch()