Update app.py

app.py

@@ -1,64 +1,43 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+# Please use transformers==4.45.0
 
-"""
-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(model="GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct")
+import torch
+import transformers
 
+model_id = "GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    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]})
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
 
-    messages.append({"role": "user", "content": message})
+terminators = [
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
 
-    response = ""
+# Javanese
+messages = [
+   {"role": "user", "content": "Sopo wae sing ana ing Punakawan?"}
+]
 
-    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
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+)
+print(outputs[0]["generated_text"][-1])
 
-        response += token
-        yield response
 
+# Sundanese
+messages = [
+    {"role": "user", "content": "Kumaha caritana si Kabayan?"},
+]
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-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.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)",
-        ),
-    ],
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+    eos_token_id=terminators,
 )
-
-
-if __name__ == "__main__":
-    demo.launch()
+print(outputs[0]["generated_text"][-1])