Update app.py

app.py

@@ -1,90 +1,20 @@
 import gradio as gr
-import torch
-from peft import PeftModel, PeftConfig
-from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-MODEL_NAME = "IlyaGusev/saiga_mistral_7b"
-DEFAULT_MESSAGE_TEMPLATE = "<s>{role}\n{content}</s>"
-DEFAULT_RESPONSE_TEMPLATE = "<s>bot\n"
-DEFAULT_SYSTEM_PROMPT = "Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им."
+# Load your custom model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
+model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 
-class Conversation:
-    def __init__(
-        self,
-        message_template=DEFAULT_MESSAGE_TEMPLATE,
-        system_prompt=DEFAULT_SYSTEM_PROMPT,
-        response_template=DEFAULT_RESPONSE_TEMPLATE
-    ):
-        self.message_template = message_template
-        self.response_template = response_template
-        self.messages = [{
-            "role": "system",
-            "content": system_prompt
-        }]
-
-    def add_user_message(self, message):
-        self.messages.append({
-            "role": "user",
-            "content": message
-        })
-
-    def add_bot_message(self, message):
-        self.messages.append({
-            "role": "bot",
-            "content": message
-        })
-
-    def get_prompt(self, tokenizer):
-        final_text = ""
-        for message in self.messages:
-            message_text = self.message_template.format(**message)
-            final_text += message_text
-        final_text += DEFAULT_RESPONSE_TEMPLATE
-        return final_text.strip()
-
-def generate(model, tokenizer, prompt, generation_config):
-    data = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
-    data = {k: v.to(model.device) for k, v in data.items()}
-    output_ids = model.generate(
-        **data,
-        generation_config=generation_config
-    )[0]
-    output_ids = output_ids[len(data["input_ids"][0]):]
-    output = tokenizer.decode(output_ids, skip_special_tokens=True)
-    return output.strip()
-
-config = PeftConfig.from_pretrained(MODEL_NAME)
-model = AutoModelForCausalLM.from_pretrained(
-    config.base_model_name_or_path,
-    load_in_8bit=True,
-    torch_dtype=torch.float16,
-    device_map="auto"
-)
-model = PeftModel.from_pretrained(
-    model,
-    MODEL_NAME,
-    torch_dtype=torch.float16
-)
-model.eval()
-
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=False)
-generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
-
-# Gradio interface setup
-def chat_with_model(user_input):
-    conversation = Conversation()
-    conversation.add_user_message(user_input)
-    prompt = conversation.get_prompt(tokenizer)
-    response = generate(model, tokenizer, prompt, generation_config)
-    conversation.add_bot_message(response)
-    return conversation.messages[-1]["content"]
+def chat_with_model(input_text):
+    input_ids = tokenizer.encode("You: " + input_text, return_tensors="pt", max_length=1024, truncation=True)
+    response_ids = model.generate(input_ids, max_length=100, num_return_sequences=1, no_repeat_ngram_size=2)
+    reply = tokenizer.decode(response_ids[0], skip_special_tokens=True)
+    return reply
 
 iface = gr.Interface(
     fn=chat_with_model,
     inputs=gr.Textbox(prompt="You:"),
     outputs=gr.Textbox(prompt="Bot:"),
-    live=True,
-    title="Chat with Bot",
 )
 
 iface.launch()