Update app.py

app.py

@@ -1,17 +1,66 @@
-from transformers import  AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
-from peft import PeftModel, PeftConfig
+from transformers import AutoTokenizer, MistralForCausalLM
 import torch
 import gradio as gr
-  
-  
+import random
+from textwrap import wrap
+import random
+
+# Functions to Wrap the Prompt Correctly
+
+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(input_text, system_prompt="", max_length=512):
+    """
+    Generates text using a large language model, given a prompt and a device.
+    Args:
+        input_text: The input text to generate a response for.
+        system_prompt: Optional system prompt.
+        max_length: Maximum length of the generated text.
+    Returns:
+        A string containing the generated text.
+    """
+    # Modify the input text to include the desired format
+    formatted_input = f"""<s>[INST]{input_text}[/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"
+
 # Use the base model's ID
 base_model_id = "mistralai/Mistral-7B-v0.1"
 model_directory = "Tonic/mistralmed"
 
-# Instantiate the Models
-tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1", trust_remote_code=True, padding_side="left")
-#tokenizer.pad_token = tokenizer.eos_token
-#tokenizer.padding_side = 'left'
+# Instantiate the Tokenizer
+# tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1", trust_remote_code=True, padding_side="left")
+tokenizer = AutoTokenizer.from_pretrained("Tonic/mistralmed", trust_remote_code=True, padding_side="left")
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = 'left'
 
 
 # Specify the configuration class for the model
@@ -29,9 +78,9 @@ class ChatBot:
     def __init__(self):
         self.history = []
 
-    def predict(self, input):
+    def predict(self, input_text):
         # Encode user input
-        user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors="pt")
+        user_input_ids = tokenizer.encode(input_text, return_tensors="pt")
 
         # Concatenate the user input with chat history
         if len(self.history) > 0:
@@ -53,7 +102,7 @@ bot = ChatBot()
 
 title = "👋🏻Welcome to Tonic's MistralMed Chat🚀"
 description = "You can use this Space to test out the current model (MistralMed) or duplicate this Space and use it for any other model on 🤗HuggingFace. Join me on Discord to build together."
-examples = [["What is the boiling point of nitrogen"]]
+examples = [["What is the boiling point of nitrogen?"]]
 
 iface = gr.Interface(
     fn=bot.predict,