special_tokens_dict = {
    'eos_token': '<|STOP|>',
    'bos_token': '<|STOP|>',
    'pad_token': '<|PAD|>',
    'additional_special_tokens': ['<|BEGIN_QUERY|>', '<|BEGIN_QUERY|>', 
                                  '<|BEGIN_ANALYSIS|>', '<|END_ANALYSIS|>',
                                  '<|BEGIN_RESPONSE|>', '<|END_RESPONSE|>',
                                  '<|BEGIN_SENTIMENT|>', '<|END_SENTIMENT|>',
                                  '<|BEGIN_CLASSIFICATION|>', '<|END_CLASSIFICATION|>',]
}

tokenizer.add_special_tokens(special_tokens_dict)
model.resize_token_embeddings(len(tokenizer))

tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids('<|STOP|>')
tokenizer.bos_token_id = tokenizer.convert_tokens_to_ids('<|STOP|>')
tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids('<|PAD|>')

The order of tokens is as follows:

python

def combine_text(user_prompt, analysis, sentiment, new_response, classification):
    user_q = f"<|STOP|><|BEGIN_QUERY|>{user_prompt}<|END_QUERY|>"
    analysis = f"<|BEGIN_ANALYSIS|>{analysis}<|END_ANALYSIS|>"
    new_response = f"<|BEGIN_RESPONSE|>{new_response}<|END_RESPONSE|>"
    sentiment = f"<|BEGIN_SENTIMENT|>Sentiment: {sentiment}<|END_SENTIMENT|><|STOP|>"
    classification = f"<|BEGIN_CLASSIFICATION|>{classification}<|END_CLASSIFICATION|>"
    return user_q + analysis + new_response + classification + sentiment

INFERANCING

I am currently testing two ways, if anyone knows a better one, please let me know!

python

import torch
from transformers import AutoModelForCausalLLM, AutoTokenizer

models_folder = "Deeokay/DialoGPT-special-tokens-medium4"

model = AutoModelForCausalLM.from_pretrained(models_folder)
tokenizer = AutoTokenizer.from_pretrained(models_folder)

# Device configuration <<change as needed>> 
device = torch.device("cpu")
model.to(device)

OPTION 1 INFERFENCE

python

import time

class Stopwatch:
    def __init__(self):
        self.start_time = None
        self.end_time = None

    def start(self):
        self.start_time = time.time()

    def stop(self):
        self.end_time = time.time()

    def elapsed_time(self):
        if self.start_time is None:
            return "Stopwatch hasn't been started"
        if self.end_time is None:
            return "Stopwatch hasn't been stopped"
        return self.end_time - self.start_time

stopwatch1 = Stopwatch()

def generate_response(input_text, max_length=250):
    
	stopwatch1.start()
    
	# Prepare the input
	# input_text = f"<|BEGIN_QUERY|>{input_text}<|END_QUERY|><|BEGIN_ANALYSIS|>{input_text}<|END_ANALYSIS|><|BEGIN_RESPONSE|>"
	input_text = f"<|BEGIN_QUERY|>{input_text}<|END_QUERY|><|BEGIN_ANALYSIS|>"
    
	input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)

	# Create attention mask
	attention_mask = torch.ones_like(input_ids).to(device)
    
	# Generate
	output = model.generate(
    	input_ids,
    	max_new_tokens=max_length,
    	num_return_sequences=1,
    	no_repeat_ngram_size=2,
    	attention_mask=attention_mask,
    	pad_token_id=tokenizer.eos_token_id,
    	eos_token_id=tokenizer.convert_tokens_to_ids('<|STOP|>'),
	)
    
	stopwatch1.stop()
	return tokenizer.decode(output[0], skip_special_tokens=False)

OPTION 2 INFERNCE

python

import time

class Stopwatch:
    def __init__(self):
        self.start_time = None
        self.end_time = None

    def start(self):
        self.start_time = time.time()

    def stop(self):
        self.end_time = time.time()

    def elapsed_time(self):
        if self.start_time is None:
            return "Stopwatch hasn't been started"
        if self.end_time is None:
            return "Stopwatch hasn't been stopped"
        return self.end_time - self.start_time

stopwatch2 = Stopwatch()

def generate_response2(input_text, max_length=250):
    
	stopwatch2.start()
    
	# Prepare the input
	# input_text = f"<|BEGIN_QUERY|>{input_text}<|END_QUERY|><|BEGIN_ANALYSIS|>{input_text}<|END_ANALYSIS|><|BEGIN_RESPONSE|>"
	input_text = f"<|BEGIN_QUERY|>{input_text}<|END_QUERY|><|BEGIN_ANALYSIS|>"
	input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)

	# Create attention mask
	attention_mask = torch.ones_like(input_ids).to(device)

	# # 2ND OPTION FOR : Generate
	output = model.generate(
    	input_ids,
    	max_new_tokens=max_length,
    	attention_mask=attention_mask,
    	do_sample=True,
    	temperature=0.4,
    	top_k=60,
    	no_repeat_ngram_size=2,
    	pad_token_id=tokenizer.pad_token_id,
    	eos_token_id=tokenizer.eos_token_id,
	)
    
	stopwatch2.stop()
	return tokenizer.decode(output[0], skip_special_tokens=False)

DECODING ANSWER

When I need just the response

python

def decode(text):
	full_text = text
    
	# Extract the response part
	start_token = "<|BEGIN_RESPONSE|>"
	end_token = "<|END_RESPONSE|>"
	start_idx = full_text.find(start_token)
	end_idx = full_text.find(end_token)
    
	if start_idx != -1 and end_idx != -1:
    	response = full_text[start_idx + len(start_token):end_idx].strip()
	else:
    	response = full_text.strip()
    
	return response

MY SETUP

I use the stopwatch to time the responses and I use both inference to see the difference

python

input_text = "Who is Steve Jobs and what was contribution?"
response1_full = generate_response(input_text)
#response1 = decode(response1_full)
print(f"Input: {input_text}")
print("=======================================")
print(f"Response1: {response1_full}")
elapsed1 = stopwatch1.elapsed_time()
print(f"Process took {elapsed1:.4f} seconds")
print("=======================================")
response2_full = generate_response2(input_text)
#response2 = decode(response2_full)
print(f"Response2: {response2_full}")
elapsed2 = stopwatch2.elapsed_time()
print(f"Process took {elapsed2:.4f} seconds")
print("=======================================")

Out-of-Scope Use

Well everything that has a factual data.. trust at your own risk!

Never tested on mathamatical knowledge.

I quite enjoy how the response feels closer to what I had in mind..