Update space

app.py

@@ -1,11 +1,15 @@
 import gradio as gr
+from llama_cpp import Llama
 from huggingface_hub import InferenceClient
 
 """
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+For more information on ⁠ huggingface_hub ⁠ Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
+llm = Llama.from_pretrained(
+    repo_id="rcarioniporras/model",
+    filename="*.gguf",
+    verbose=False
+)
 
 def respond(
     message,
@@ -26,8 +30,7 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
+    for message in llm.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
@@ -39,7 +42,6 @@ def respond(
         response += token
         yield response
 
-
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
@@ -59,6 +61,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+if __name__ == "main":
+    demo.launch()

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+llama_cpp
+gradio