Update README.md

README.md

@@ -14,6 +14,7 @@ pipeline_tag: question-answering
 
 This is a medical fine tuned model from the [Falcon-7b-Instruction](https://huggingface.co/tiiuae/falcon-7b-instruct) Base using 500 steps & 6 epochs with [MedAware](https://huggingface.co/datasets/keivalya/MedQuad-MedicalQnADataset) Dataset from [keivalya](https://huggingface.co/datasets/keivalya)
 
+Check out a cool demo with chat memory here : [pseudolab/GaiaFalconChat](https://huggingface.co/spaces/pseudolab/GaiaMiniMed_ChatWithFalcon)
 
 ## Model Details
 
@@ -29,7 +30,7 @@ This is a medical fine tuned model from the [Falcon-7b-Instruction](https://hugg
 ### Model Sources 
 
 - **Repository:** [Github](https://github.com/Josephrp/AI-challenge-hackathon/blob/master/falcon_7b_instruct_GaiaMiniMed_dataset.ipynb)
-- **Demo :** [pseudolab/gaiaminimed](https://huggingface.co/spaces/pseudolab/gaiaminimed) & [tonic/gaiaminimed](https://huggingface.com/spaces/tonic/gaiaminimed)
+- **Demo :** [pseudolab/gaiafalconchat](https://huggingface.co/spaces/pseudolab/GaiaMiniMed_ChatWithFalcon)[pseudolab/gaiaminimed](https://huggingface.co/spaces/pseudolab/gaiaminimed) & [tonic/gaiaminimed](https://huggingface.com/spaces/tonic/gaiaminimed)
 
 ## Uses
 
@@ -67,6 +68,8 @@ Use the code below to get started with the model.
 
 ```python
 
+# Gaia Mini Med Quick Start
+
 from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
 from peft import PeftModel, PeftConfig
 import torch
@@ -142,6 +145,170 @@ iface.launch()
 
 ```
 
+See the code below for more advanced deployment , including a naive memory store and user controllable parameters:
+
+```Python
+
+# Welcome to a more advanced implementation of Gaia Mini Med - Falcon Chat
+
+from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel, PeftConfig
+import torch
+import gradio as gr
+import json
+import os
+import shutil
+import requests
+
+# Define the device
+device = "cuda" if torch.cuda.is_available() else "cpu"
+#Define variables 
+temperature=0.4
+max_new_tokens=240
+top_p=0.92
+repetition_penalty=1.7
+max_length=2048
+
+# Use model IDs as variables
+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'
+
+
+# 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 = AutoConfig.from_pretrained(base_model_id)
+# Load the PEFT model with the specified configuration
+peft_model = AutoModelForCausalLM.from_pretrained(model_directory, config=model_config)
+peft_model = PeftModel.from_pretrained(peft_model, model_directory)
+
+
+
+# Class to encapsulate the Falcon chatbot
+class FalconChatBot:
+    def __init__(self, system_prompt="You are an expert medical analyst:"):
+        self.system_prompt = system_prompt
+
+    def process_history(self, history):
+        if history is None:
+            return []
+        
+        # Ensure that history is a list of dictionaries
+        if not isinstance(history, list):
+            return []
+        
+        # Filter out special commands from the history
+        filtered_history = []
+        for message in history:
+            if isinstance(message, dict):
+                user_message = message.get("user", "")
+                assistant_message = message.get("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, user_message, assistant_message, history, temperature=0.4, max_new_tokens=700, top_p=0.99, repetition_penalty=1.9):
+
+        # Process the history to remove special commands
+        processed_history = self.process_history(history)
+        # Combine the user and assistant messages into a conversation
+        conversation = f"{self.system_prompt}\nFalcon: {assistant_message if assistant_message else ''} User: {user_message}\nFalcon:\n"
+        # Encode the conversation using the tokenizer
+        input_ids = tokenizer.encode(conversation, return_tensors="pt", add_special_tokens=False)
+        # Generate a response using the Falcon model
+        response = peft_model.generate(input_ids=input_ids, max_length=max_length, 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)
+        # Decode the generated response to text
+        response_text = tokenizer.decode(response[0], skip_special_tokens=True)
+        # Append the Falcon-like conversation to the history
+        self.history.append(conversation)
+        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 = [  
+    [  
+        "Assistant is a public health and medical expert named Gaia ready to help the user.",   
+        "Hi there, I have a question!",   
+        "My name is Gaia, I'm a health and sanitation expert ready to answer your medical questions.",   
+        "Assistant is a medical and sanitation question expert trained to answer medical questions", 0.4, 700, 0.90, 1.9  
+    ]
+]  
+
+
+additional_inputs=[
+    gr.Textbox("", label="Optional system prompt"),
+    gr.Slider(
+        label="Temperature",
+        value=0.9,
+        minimum=0.0,
+        maximum=1.0,
+        step=0.05,
+        interactive=True,
+        info="Higher values produce more diverse outputs",
+    ),
+    gr.Slider(
+        label="Max new tokens",
+        value=256,
+        minimum=0,
+        maximum=3000,
+        step=64,
+        interactive=True,
+        info="The maximum numbers of new tokens",
+    ),
+    gr.Slider(
+        label="Top-p (nucleus sampling)",
+        value=0.90,
+        minimum=0.01,
+        maximum=0.99,
+        step=0.05,
+        interactive=True,
+        info="Higher values sample more low-probability tokens",
+    ),
+    gr.Slider(
+        label="Repetition penalty",
+        value=1.2,
+        minimum=1.0,
+        maximum=2.0,
+        step=0.05,
+        interactive=True,
+        info="Penalize repeated tokens",
+    )
+]
+
+iface = gr.Interface(
+    fn=falcon_bot.predict,
+    title=title,
+    description=description,
+    examples=examples,
+    inputs=[
+        gr.inputs.Textbox(label="System Prompt", type="text", lines=2),
+        gr.inputs.Textbox(label="User Message", type="text", lines=3),
+        gr.inputs.Textbox(label="Assistant Message", type="text", lines=2),
+    ] + additional_inputs,
+    outputs="text",
+    theme="ParityError/Anime"
+)
+
+# Launch the Gradio interface for the Falcon model
+iface.launch()
+
+```
+
+
 ## Training Details
 
 ### Results