Update app.py

app.py

@@ -1,69 +1,30 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
+model_name = "Hitelcy/sarvix-multilingual-1"
 
-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")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        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,
-    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)",
-        ),
-    ],
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float32,  # CPU doesn't support fp16 well, use float32
+    device_map="cpu"
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+def clarify(user_input):
+    prompt = f"<|im_start|>user\n{user_input}<|im_end|>\n<|im_start|>assistant\n"
+    inputs = tokenizer(prompt, return_tensors="pt")
+    out = model.generate(**inputs, max_new_tokens=60)
+    response = tokenizer.decode(out[0], skip_special_tokens=True)
+    # Extract just the assistant's reply, stripping the prompt echo
+    response = response.split("assistant\n")[-1].strip()
+    return response
+
+demo = gr.Interface(
+    fn=clarify,
+    inputs=gr.Textbox(label="Your message"),
+    outputs=gr.Textbox(label="Clarification"),
+    title="Sarvix Clarify",
+)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()