reverting the changes

app.py

@@ -1,12 +1,11 @@
 import gradio as gr
-from ctransformers import AutoModelForCausalLM
+from huggingface_hub import InferenceClient
 
-# Use ctransformers for GGUF models
-client = AutoModelForCausalLM.from_pretrained(
-    "michailroussos/model-mistral_CP1250", 
-    model_type='mistral',
-    gpu_layers=0  # Set to 0 for CPU, or appropriate number for GPU
-)
+"""
+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")
+client = InferenceClient("michailroussos/lora_model-mistral_t2")
 
 def respond(
     message,
@@ -16,19 +15,34 @@ def respond(
     temperature,
     top_p,
 ):
-    # Combine system message and current message
-    full_prompt = f"{system_message}\n{message}"
-    
-    # Generate response
-    response = client(
-        full_prompt, 
-        max_new_tokens=max_tokens,
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
         temperature=temperature,
-        top_p=top_p
-    )
-    
-    return response
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
 
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -45,5 +59,6 @@ demo = gr.ChatInterface(
     ],
 )
 
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1,5 +1 @@
-huggingface_hub==0.25.2
-transformers==4.47.0
-torch
-ctransformers
-gradio
+huggingface_hub==0.25.2