Update README.md

README.md

@@ -66,120 +66,78 @@ See the [author's demo](https://huggingface.co/spaces/tonic/gaiaminimed)
 Use the code below to get started with the model.
 
 ```python
-from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM
+
+from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
 from peft import PeftModel, PeftConfig
 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
+
+def multimodal_prompt(user_input, system_prompt="You are an expert medical analyst:"):
+    formatted_input = f"{{{{ {system_prompt} }}}}\nUser: {user_input}\nFalcon:"
+    encodeds = tokenizer(formatted_input, return_tensors="pt", add_special_tokens=False)
+    model_inputs = encodeds.to(device)
+    output = model.generate(
+        **model_inputs,
+        max_length=500,
+        use_cache=True,
+        early_stopping=False,
+        bos_token_id=peft_model.config.bos_token_id,
+        eos_token_id=peft_model.config.eos_token_id,
+        pad_token_id=peft_model.config.eos_token_id,
+        temperature=0.4,
+        do_sample=True
+    )
+    response_text = tokenizer.decode(output[0], skip_special_tokens=True)
 
-# Define the device
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
+    return response_text
 
-# Use model IDs as variables
+device = "cuda" if torch.cuda.is_available() else "cpu"
 base_model_id = "tiiuae/falcon-7b-instruct"
 model_directory = "Tonic/GaiaMiniMed"
 
-# Instantiate the Tokenizer
 tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True, padding_side="left")
-tokenizer.pad_token = tokenizer.eos_token
-tokenizer.padding_side = 'left'
-
-# Define the PeftConfig
-#peft_config = PeftConfig(
-#    max_length=500,
-#    use_cache=True,
-#    early_stopping=False,
-#    bos_token_id=tokenizer.bos_token_id,  # Use the tokenizer's BOS token ID
-#    eos_token_id=tokenizer.eos_token_id,  # Use the tokenizer's EOS token ID
-#    pad_token_id=tokenizer.eos_token_id,  # Use the tokenizer's EOS token ID
-#    temperature=0.4,
-#    do_sample=True
-#)
-
-
-# Load the GaiaMiniMed model with the specified configuration
-# Load the Peft model with a specific configuration
-# Specify the configuration class for the model
-model_config = PeftConfig.from_pretrained(model_directory) #use base falcon config
-# Load the PEFT model with the specified configuration
-peft_model = AutoModelForCausalLM.from_pretrained(base_model_id, config=model_config)
-peft_model = PeftModel.from_pretrained(model="Tonic/GaiaMiniMed")
-peft_model = PeftModel.from_pretrained(peft_model, "Tonic/GaiaMiniMed")
-
-
-
-# Class to encapsulate the Falcon chatbot
-class FalconChatBot:
+model_config = AutoConfig.from_pretrained(base_model_id)
+peft_model = AutoModelForCausalLM.from_pretrained(model_directory, config=model_config)
+peft_model = PeftModel.from_pretrained(peft_model, model_directory)
+class ChatBot:
     def __init__(self, system_prompt="You are an expert medical analyst:"):
         self.system_prompt = system_prompt
+        self.history = []
 
-    def process_history(self, history):
-        # Filter out special commands from the history
-        filtered_history = []
-        for message in history:
-            user_message = message["user"]
-            assistant_message = message["assistant"]
-            # Check if the user_message is not a special command
-            if not user_message.startswith("Falcon:"):
-                filtered_history.append({"user": user_message, "assistant": assistant_message})
-        return filtered_history
-
-    def predict(self, input_data, max_length=500):
-        # Extract messages from the input data
-        preprompt = input_data["preprompt"]
-        history = input_data["history"]
-
-        # Process the history to remove special commands
-        processed_history = self.process_history(history)
-
-        # Generate the formatted conversation in Falcon message format
-        conversation = f"{preprompt}\n"
-        for message in processed_history:
-            user_message = message["user"]
-            assistant_message = message["assistant"]
-            conversation += f"Falcon:{' ' + assistant_message if assistant_message else ''} User: {user_message}\n Falcon:\n"
-
-        # Encode the formatted conversation using the tokenizer
-        input_ids = tokenizer.encode(conversation, return_tensors="pt", add_special_tokens=False)
-
-        # Generate a response using the Falcon model
-        response = falcon_model.generate(input_ids, max_length=max_length, use_cache=True, early_stopping=True, bos_token_id=falcon_model.config.bos_token_id, eos_token_id=falcon_model.config.eos_token_id, pad_token_id=falcon_model.config.eos_token_id, temperature=0.4, do_sample=True)
-
-        # Decode the generated response to text
+    def predict(self, user_input, system_prompt):
+        formatted_input = f"{{{{ {self.system_prompt} }}}}\nUser: {user_input}\nFalcon:"
+        input_ids = tokenizer.encode(formatted_input, return_tensors="pt", add_special_tokens=False)
+        response = peft_model.generate(input_ids, max_length=900, use_cache=False, early_stopping=False, bos_token_id=peft_model.config.bos_token_id, eos_token_id=peft_model.config.eos_token_id, pad_token_id=peft_model.config.eos_token_id, temperature=0.4, do_sample=True)
         response_text = tokenizer.decode(response[0], skip_special_tokens=True)
+        self.history.append(formatted_input)
+        self.history.append(response_text)
 
         return response_text
 
-# Create the Falcon chatbot instance
-falcon_bot = FalconChatBot()
-
-# Define the Gradio interface
-title = "👋🏻Welcome to Tonic's 🦅Falcon's Medical👨🏻‍⚕️Expert Chat🚀"
-description = "You can use this Space to test out the GaiaMiniMed model [(Tonic/GaiaMiniMed)](https://huggingface.co/Tonic/GaiaMiniMed) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
-examples = [{
-    "preprompt": "system message",
-    "history": [{
-        "user": "user message 1",
-        "assistant": "assistant message 1"
-    }, {
-        "user": "user message 1",
-        "assistant": None
-    }]
-}]
+bot = ChatBot()
+
+title = "👋🏻Welcome to Tonic's GaiaMiniMed Chat🚀"
+description = "You can use this Space to test out the current model [(Tonic/GaiaMiniMed)](https://huggingface.co/Tonic/GaiaMiniMed) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
+examples = [["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"]]
 
 iface = gr.Interface(
-    fn=falcon_bot.predict,
+    fn=bot.predict,
     title=title,
     description=description,
     examples=examples,
-    inputs=[
-        gr.inputs.Textbox(label="Input Data", type="json"),
-    ],
+    inputs=["text", "text"],  
     outputs="text",
     theme="ParityError/Anime"
 )
 
-# Launch the Gradio interface for the Falcon model
 iface.launch()
 
 ```