Update app.py

app.py

@@ -1,70 +1,50 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load model once
+model_name = "fla-hub/rwkv7-2.9B-world"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    trust_remote_code=True,
+    torch_dtype=torch.float32,
+    low_cpu_mem_usage=True,
+    device_map="cpu"
+)
 
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
+    for h in history:
+        messages.append({"role": "user", "content": h[0]})
+        messages.append({"role": "assistant", "content": h[1]})
     messages.append({"role": "user", "content": message})
+    
+    text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    inputs = tokenizer(text, return_tensors="pt")
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id
+        )
+    
+    response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
+    return response
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     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.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.Textbox(value="You are a helpful assistant.", label="System message"),
+        gr.Slider(1, 512, 256, step=1, label="Max tokens"),
+        gr.Slider(0.1, 2.0, 0.7, step=0.1, label="Temperature"),
+        gr.Slider(0.1, 1.0, 0.9, step=0.05, label="Top-p"),
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+chatbot.launch()