Update app.py

app.py

@@ -1,63 +1,151 @@
 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("HuggingFaceH4/zephyr-7b-beta")
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+import torch
+
+# Initialize the InferenceClient
+
+client = InferenceClient("01-ai/Yi-Coder-9B-Chat")
 
+# Initialize tokenizer and model
+
+model_path = "01-ai/Yi-Coder-9B-Chat"  # Make sure this is correct
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto").eval()
 
 def respond(
+
     message,
+
     history: list[tuple[str, str]],
+
     system_message,
+
     max_tokens,
+
     temperature,
+
     top_p,
+
+    use_local_model: bool,
+
 ):
+
     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]})
+    for user, assistant in history:
+
+        if user:
+
+            messages.append({"role": "user", "content": user})
+
+        if assistant:
+
+            messages.append({"role": "assistant", "content": assistant})
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    if use_local_model:
+
+        # Use local model
+
+        input_ids = tokenizer.encode("".join([m["content"] for m in messages]), return_tensors="pt")
+
+        input_ids = input_ids.to(model.device)
+
+        
+
+        with torch.no_grad():
+
+            output = model.generate(
+
+                input_ids,
+
+                max_new_tokens=max_tokens,
+
+                temperature=temperature,
+
+                top_p=top_p,
+
+                do_sample=True,
+
+                pad_token_id=tokenizer.eos_token_id,
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+            )
+
+        
+
+        response = tokenizer.decode(output[0], skip_special_tokens=True)
 
-        response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    else:
+
+        # Use Hugging Face Inference API
+
+        response = ""
+
+        for message in client.text_generation(
+
+            "".join([m["content"] for m in messages]),
+
+            max_new_tokens=max_tokens,
+
+            stream=True,
+
+            temperature=temperature,
+
+            top_p=top_p,
+
+        ):
+
+            response += message
+
+            yield response
+
+# Create Gradio interface
+
 demo = gr.ChatInterface(
+
     respond,
+
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+
+        gr.Textbox(value="Odpowiadasz w Jezyku Polskim jesteś Coder/Developer/Programista tworzysz pełny kod..", label="System message"),
+
+        gr.Slider(minimum=1, maximum=2048, value=2048, step=1, label="Max new tokens"),
+
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+
         gr.Slider(
+
             minimum=0.1,
+
             maximum=1.0,
+
             value=0.95,
+
             step=0.05,
+
             label="Top-p (nucleus sampling)",
+
         ),
+
+        gr.Checkbox(label="Use Local Model", value=False),
+
     ],
+
+    title="Advanced Chat Interface",
+
+    description="Chat with an AI model using either the Hugging Face Inference API or a local model.",
+
 )
 
+if name == "__main__":
 
-if __name__ == "__main__":
     demo.launch()