Update app.py

app.py

@@ -1,88 +1,44 @@
 import spaces
-from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 import gradio as gr
-import random
-from textwrap import wrap
 
-def wrap_text(text, width=90):
-    lines = text.split('\n')
-    wrapped_lines = [textwrap.fill(line, width=width) for line in lines]
-    wrapped_text = '\n'.join(wrapped_lines)
-    return wrapped_text
+title = "# 🚀👋🏻Welcome to Tonic's🤖SuperAGI/SAM🚀"
+description = """SAM is an Agentic-Native LLM that **excels at complex reasoning**. 
+You can also use [🤖SuperAGI/SAM](https://huggingface.co/SuperAGI/SAM) by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic/superagi-sam?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3> 
+Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's🛠️community 👻  [![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/GWpVpekp) On 🤗Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to 🌟 [EasyAGI](https://github.com/tonic-ai/EasyAGI) 🤗Big thanks to Ythe folks at huggingface for the ZeroGPU 🤗
+To contribute to this space make a PR with a new example or cool new use-case for this one 🤗
+"""
 
-@spaces.GPU
-def multimodal_prompt(user_input, system_prompt="You are an expert medical analyst:"):
-    # Combine user input and system prompt
-    formatted_input = f"<s> [INST] {example_instruction} [/INST] {example_answer}</s> [INST] {system_prompt} [/INST]"
-
-    # Encode the input text
-    encodeds = tokenizer(formatted_input, return_tensors="pt", add_special_tokens=False)
-    model_inputs = encodeds.to(device)
-
-    # Generate a response using the model
-    output = model.generate(
-        **model_inputs,
-        max_length=max_length,
-        use_cache=True,
-        early_stopping=True,
-        bos_token_id=model.config.bos_token_id,
-        eos_token_id=model.config.eos_token_id,
-        pad_token_id=model.config.eos_token_id,
-        temperature=0.1,
-        do_sample=True
-    )
-
-    # Decode the response
-    response_text = tokenizer.decode(output[0], skip_special_tokens=True)
-
-    return response_text
-
-# Define the device
-device = "cuda" if torch.cuda.is_available() else "cpu"
+examples = [["[Question:] What is the proper treatment for buccal herpes?", "You are a medicine and public health expert, you will receive a question, answer the question, and provide a complete answer"]]
 
-# Use the base model's ID
 model_id = "SuperAGI/SAM"
-
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-# tokenizer.pad_token = tokenizer.eos_token
-# tokenizer.padding_side = 'left'
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
 
-# Specify the configuration class for the model
-#model_config = AutoConfig.from_pretrained(base_model_id)
+@spaces.GPU
+def generate_response(formatted_input):
+    inputs = tokenizer(formatted_input, return_tensors="pt")
+    inputs = {k: v.to("cuda") for k, v in inputs.items()}
 
-model = AutoModelForCausalLM.from_pretrained(model_id , torch_dtype=torch.float16 , device_map= "auto" )
+    # Generate a response using the model
+    output = model.generate(**inputs, max_length=512, pad_token_id=tokenizer.eos_token_id)
 
+    return tokenizer.decode(output[0], skip_special_tokens=True)
 
 class ChatBot:
     def __init__(self):
-        # Initialize the ChatBot class with an empty history
         self.history = []
 
-    def predict(self, user_input, system_prompt="You are an expert medical analyst:" , example_instruction="produce a json", example_answer = "please dont make small talk "):
-        # Combine the user's input with the system prompt
-        formatted_input = f"<s> [INST] {example_instruction} [/INST] {example_answer}</s> [INST] {system_prompt} [/INST]"
-
-        # Encode the formatted input using the tokenizer
-        user_input_ids = tokenizer.encode(formatted_input, return_tensors="pt")
-
-        # Generate a response using the PEFT model
-        response = model.generate(input_ids=user_input_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)
-
-        # Decode the generated response to text
-        response_text = tokenizer.decode(response[0], skip_special_tokens=True)
-        
-        return response_text  # Return the generated response
+    def predict(self, example_instruction, example_answer, user_input, system_prompt):
+        formatted_input = f"<s> [INST] {example_instruction} [/INST] {example_answer}</s> [INST] {system_prompt} {user_input} [/INST]"
+        return generate_response(formatted_input)
 
 bot = ChatBot()
 
-title = "🚀👋🏻Welcome to Tonic's🤖SuperAGI/SAM Chat🚀"
-description = "SAM is an Agentic-Native LLM that excels at complex reasoning. You can use this Space to test out the current model [Tonic/superagi-sam](https://huggingface.co/Tonic/superagi-sam) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
-examples = [["[Question:] What is the proper treatment for buccal herpes?", "You are a medicine and public health expert, you will receive a question, answer the question, and provide a complete answer"]]
-
-
 def main():
     with gr.Blocks() as demo:
+
         gr.Markdown(title)
         gr.Markdown(description)
         with gr.Row():
@@ -104,4 +60,4 @@ def main():
     demo.launch()
 
 if __name__ == "__main__":
-    main()
+    main()