Update app.py

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
-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
-"""
-client = InferenceClient("Aksh1t/mistral-7b-oig-unsloth-merged")
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
+# Load the tokenizer and model
+model_name = "Aksh1t/mistral-7b-oig-unsloth-merged"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
 
 def respond(
     message,
@@ -15,33 +14,32 @@ def respond(
     temperature,
     top_p,
 ):
-    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,
+    # Construct the prompt
+    prompt = system_message + "\n"
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            prompt += f"User: {user_msg}\n"
+        if assistant_msg:
+            prompt += f"Assistant: {assistant_msg}\n"
+    prompt += f"User: {message}\nAssistant:"
+
+    # Encode the prompt and generate a response
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        inputs.input_ids,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        do_sample=True
+    )
+
+    # Decode the generated response
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-        response += token
-        yield response
+    # Extract the assistant's reply
+    assistant_reply = response.split("Assistant:")[-1].strip()
+    yield assistant_reply
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +56,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()