corpus = """ Hey, how have you been doing lately? Hello, I’ve been doing quite well, thank you! I’ve just been really busy with my work and projects. That’s great to hear! What exactly has been keeping you occupied these days? I’m currently working on a big project at my job that has a very tight deadline, so it has been quite hectic. That sounds pretty stressful! How are you managing to handle all of that? Hi, I’m trying my best to stay organized and make sure I take breaks whenever I can to clear my mind. That’s a smart approach! Have you had any time to relax and unwind at all? Not really, to be honest, but I am planning to take a weekend trip soon to get away for a bit. That sounds like a fantastic idea! Where are you thinking of going for your trip? I’m considering going to the beach because I really need some sun and a nice sandy place to relax. That would be so refreshing! Do you have a favorite beach spot that you like to visit? Yes, I absolutely love going to the beach that’s near my hometown. It’s always been my favorite. Nice! How often do you get the chance to visit that beach? Not nearly as often as I would like, maybe just once a year if I’m lucky enough to find the time. I understand completely; life can get really busy sometimes. What do you usually enjoy doing when you’re there? I love swimming in the ocean, reading a good book, and just relaxing by the water while listening to the waves. That sounds absolutely perfect! Have you read any good books lately? Yes, I just finished reading a really good mystery novel that kept me guessing the whole time. I love a good mystery! What was the title of the book you just finished? The book was called "The Silent Patient," and I would highly recommend it to anyone who enjoys that genre. I’ve heard a lot of great things about that book! I’ll definitely add it to my reading list for sure. You really should! It has such an amazing twist at the end that you won’t see coming. I love a good twist in a story! Do you read often, or do you find it hard to make time for it? I try to read a little bit every night before I go to bed to help me relax. That’s a wonderful habit! I usually end up watching TV instead of reading. What shows are you currently watching? I’ve been really into a lot of crime dramas lately; they are always so captivating. Those shows can be really gripping! Do you have any favorites that you would recommend? I really enjoy "Mindhunter" and "True Detective." They are both so well done! Both of those are excellent shows! I’ve seen "Mindhunter," and I thought it was amazing! Right? The psychological aspects and character development are just fascinating to watch. I completely agree! Do you also like watching documentaries in your free time? Yes, I especially enjoy true crime documentaries; they always tell such interesting stories. Same here! There are so many fascinating documentaries out there to watch. Absolutely! I could easily binge-watch them for hours without getting bored. What was the last documentary you watched that you found particularly interesting? I recently watched "The Staircase," and it was so intense and thought-provoking. I’ve heard really good things about that documentary! I’ll definitely check it out when I have some time. You should absolutely do that! I think you won’t regret it at all; it’s very compelling. Thanks for the recommendation! I’m always looking for something new to watch. No problem! I’m glad to share. Let me know what you think once you watch it! Will do! It’s always nice to have someone to discuss these things with. I agree! It makes watching shows and reading books much more enjoyable when you can talk about them. Definitely! Let’s keep sharing recommendations. For sure! I’m looking forward to it! 2 + 2 = 4 3 + 5 = 8 10 + 7 = 17 20 - 5 = 15 18 - 7 = 11 50 - 25 = 25 4 * 3 = 12 6 * 6 = 36 7 * 5 = 35 8 * 4 = 32 15 / 3 = 5 12 / 4 = 3 9 / 3 = 3 25 + 30 = 55 45 - 15 = 30 100 / 10 = 10 40 * 2 = 80 81 / 9 = 9 16 + 24 = 40 9 * 7 = 63 72 / 8 = 9 13 + 14 = 27 90 - 33 = 57 22 * 3 = 66 54 / 6 = 9 27 + 32 = 59 80 / 5 = 16 11 * 9 = 99 64 - 14 = 50 5 + 8 = 13 3 * 7 = 21 49 / 7 = 7 19 + 23 = 42 77 - 28 = 49 48 / 4 = 12 9 * 8 = 72 35 + 17 = 52 88 / 8 = 11 50 - 30 = 20 4 * 11 = 44 36 / 6 = 6 5 + 10 = 15 7 * 4 = 28 72 - 18 = 54 80 / 10 = 8 60 * 2 = 120 2 + 3 = 5 25 - 10 = 15 14 * 2 = 28 28 / 4 = 7 90 + 10 = 100 56 - 36 = 20 3 * 12 = 36 45 / 5 = 9 33 + 66 = 99 100 - 50 = 50 8 * 9 = 72 10 / 2 = 5 14 + 6 = 20 21 - 9 = 12 6 * 7 = 42 35 / 5 = 7 15 + 15 = 30 8 - 3 = 5 16 / 2 = 8 50 * 1 = 50 Hey, how have you been doing lately, {name}? Hello, I’ve been doing quite well, thank you! Just been really busy with my work and projects. That’s great to hear! What exactly has been keeping you occupied these days? I’m currently working on a big project at my job that has a very tight deadline, so it has been quite hectic. That sounds pretty stressful! How are you managing to handle all of that? I’m trying my best to stay organized and make sure I take breaks whenever I can to clear my mind. That’s a smart approach! Have you had any time to relax and unwind at all? Not really, to be honest, but I am planning to take a weekend trip soon to get away for a bit. That sounds like a fantastic idea! Where are you thinking of going for your trip, {username}? I’m considering going to the beach because I really need some sun and a nice sandy place to relax. That would be so refreshing! Do you have a favorite beach spot that you like to visit? Yes, I absolutely love going to the beach that’s near my hometown. It’s always been my favorite. Nice! How often do you get the chance to visit that beach? Not nearly as often as I would like, maybe just once a year if I’m lucky enough to find the time. I understand completely; life can get really busy sometimes. What do you usually enjoy doing when you’re there? I love swimming in the ocean, reading a good book, and just relaxing by the water while listening to the waves. That sounds absolutely perfect! Have you read any good books lately? Yes, I just finished reading a really good mystery novel that kept me guessing the whole time. I love a good mystery! What was the title of the book you just finished? The book was called "The Silent Patient," and I would highly recommend it to anyone who enjoys that genre. I’ve heard a lot of great things about that book! I’ll definitely add it to my reading list for sure. You really should! It has such an amazing twist at the end that you won’t see coming. I love a good twist in a story! Do you read often, or do you find it hard to make time for it? I try to read a little bit every night before I go to bed to help me relax. That’s a wonderful habit! I usually end up watching TV instead of reading. What shows are you currently watching? I’ve been really into a lot of crime dramas lately; they are always so captivating. Hello! Are you available for a conversation at the moment? Absolutely! I was just organizing my workspace, but I’m free to chat. What's on your mind? Well, I was pondering some interesting subjects today, like artificial intelligence, global warming, and even ancient civilizations. Those are certainly diverse topics! AI and climate change are very current, while ancient civilizations take us way back. Any reason they’re on your mind? I read an article discussing how modern technology could help us better understand historical mysteries, like lost cities. It made me curious. Fascinating! It’s amazing to think that drones, for example, can map unexplored jungles and reveal new archaeological sites. Yes! Plus, machine learning models can analyze patterns in data from those sites, potentially leading to discoveries about past cultures. Technology truly is changing our approach to history. Imagine the advancements we’ll see in just a decade! Exactly. Speaking of the future, how do you feel about space exploration and the possibilities of finding life beyond Earth? Oh, I’m thrilled about it! The concept of extraterrestrial life fascinates me. Did you hear about recent findings on potential biosignatures in distant planets? Yes! Scientists recently observed something that might indicate biological processes in the atmosphere of an exoplanet. Incredible! If confirmed, it could redefine our understanding of biology and life’s adaptability in the universe. Agreed! It’s thrilling to imagine what might be out there, waiting to be discovered. It’s moments like these that remind me of how vast and mysterious the universe is. True. And it makes our everyday problems feel a bit smaller in comparison. Absolutely. Speaking of everyday things, do you enjoy stargazing? Yes! There’s something peaceful about looking up and seeing the stars, knowing they’ve been there for billions of years. Couldn’t agree more. It’s like a reminder of continuity, that life just keeps going on, in its own way. And we’re part of that vast timeline, just a tiny part of something much larger. It's a humbling thought. Indeed. Well, this was a really enjoyable conversation. Thanks for chatting with me about all these interesting topics! Absolutely, I had a great time too! Conversations like this really make you think. Agreed! Let's do this again sometime soon. Definitely! Take care, and have a wonderful rest of your day. You too! Goodbye! bye! nice talking to you! 23 + 12 = 35 9 * 5 = 45 60 - 22 = 38 40 / 5 = 8 18 * 2 = 36 100 - 25 = 75 56 / 7 = 8 34 + 21 = 55 7 * 6 = 42 81 - 36 = 45 72 / 6 = 12 15 + 19 = 34 90 / 9 = 10 14 * 4 = 56 45 + 25 = 70 99 - 47 = 52 11 * 8 = 88 48 / 3 = 16 13 + 16 = 29 85 - 20 = 65 22 / 2 = 11 16 * 5 = 80 30 + 45 = 75 70 - 33 = 37 40 * 3 = 120 36 / 4 = 9 29 + 32 = 61 92 - 50 = 42 13 * 7 = 91 24 / 8 = 3 15 + 25 = 40 72 - 22 = 50 5 * 9 = 45 100 / 5 = 20 66 + 12 = 78 88 - 28 = 60 45 * 2 = 90 36 / 3 = 12 19 + 8 = 27 74 - 39 = 35 55 / 5 = 11 8 * 10 = 80 64 + 9 = 73 47 - 17 = 30 (3 + 5) * 2 = 16 4 ^ 3 = 64 (20 - 5) + 3 * 2 = 31 8 % 3 = 2 7! = 5040 6 ^ 2 + (3 * 5) - 4 = 41 15 * (2 + 3) - 4 ^ 2 = 51 10! / (5! * 5!) = 252 (12 + 8) / 4 + 5! = 125 (8 + 4) * 3 - 2 ^ 4 = 20 30 % 7 = 2 5 * (6 + 4) - 3 = 47 9 + 3! * (4 ^ 2) = 57 50 % 6 = 2 (25 + 5) * 2 ^ 3 = 240 (7 ^ 2) - (5 * 3) + 9 = 25 9! / (3! * 6!) = 84 (8 * 4) + (3 ^ 3) - 10 = 41 100 - 7 * 3 + 5! = 79 15 * 3 + (7 - 2) ^ 2 = 64 4! * 2 ^ 3 = 192 8 ^ 2 - 5 * 7 + 20 / 4 = 35 (9 + 7) % 5 = 1 11! / (8! * 3!) = 165 (10 ^ 2) + (6 * 3) - 15 = 75 5 + 7! / (4! * 3!) = 36 48 % (7 + 2) = 3 (6 ^ 2) + 4! - 18 = 50 12 ^ 2 - (3 * 5) + 20 = 139 100 - (8 * 3) + 2 ^ 4 = 92 (7 ^ 3) - 5! = 293 (5 * 3!) + 4 ^ 2 = 56 60 % 8 + (7 * 3) - 2 = 23 9! / (4! * 5!) = 126 (16 / 4) + 6 ^ 2 - 10 = 32 15 * (7 % 5) + 3 ^ 3 = 42 (3 + 7) * (2 ^ 3) - 10 = 54 5! + (4 * 3) - 2 ^ 3 = 118 (9 * 2 + 6) / 3 = 8 13 % 5 + 7! = 5041 8 ^ 2 - (5 * 3) + 4! = 101 (7 + 3) * (12 - 5) + 6 ^ 2 = 102 100 / (5 * 2) + 3! = 26 (15 - 4) * 3 + 2 ^ 3 = 41 (6 + 2) * (4! - 10) = 116 14 % 3 + (7 * 5) - 4 ^ 2 = 29 6! - 50 + (8 * 3) = 678 8 * 5 + 2! * 3 ^ 2 = 64 3 ^ 3 + (20 / 4) * 7 - 5 = 49 (30 - 5) % 4 * 3 + 6 ^ 2 = 37 10! / (6! * 4!) + 3! = 216 15 * 2 ^ 2 - 5! = -15 (5 ^ 2) + (4 * 3!) - 20 = 38 100 % (15 - 5) + 6 * 3 ^ 2 = 64 7! / (5! * 2!) + 4 ^ 3 = 80 (9 ^ 2) - 7 * (3 + 5) = 37 (12 + 8) * (3! - 4) = 80 11! / (8! * 3!) + 2 ^ 4 = 181 8 * 7 % 5 + 9! = 3628803 (25 - 5) * (7 - 2 ^ 2) = 75 (4 ^ 3) - (6 * 5) + 7! / 3! = 164 40 - (5 * 3) + 4! = 31 (10 + 20) * (5 - 3) ^ 2 = 120 20! / (15! * 5!) = 15504 (6 + 9) * 2 ^ (3 - 1) = 60 100 % 9 + (6 * 3!) = 52 11 ^ 2 - (4 * 8) + 2 ^ 5 = 85 (15 - 7) * (4 + 6) - 9 = 71 (8 + 5) * (9 % 4) + 10! / (5! * 5!) = 67 7 ^ 2 + (4 * 2) - 6! = -602 (6 + 5!) * (3 ^ 2 - 10) = 90 """ import math import re import random ModelName = 'AgGPT-4mini' output_length = 15 # Set the maximum number of words to generate creativity = 0.2 # Set the creativity level from 0 (rigid) to 1 (creative) UserName = 'User' # put your name here def mat_mul(A, B): result = [] for i in range(len(A)): result.append([]) for j in range(len(B[0])): result[i].append(sum(A[i][k] * B[k][j] for k in range(len(B)))) return result def softmax(x): exp_x = [math.exp(v - max(x)) for v in x] sum_exp_x = sum(exp_x) return [e / sum_exp_x for e in exp_x] def self_attention(Q, K, V): scores = [] for i in range(len(Q)): row = [] for j in range(len(K)): score = sum(Q[i][idx] * K[j][idx] for idx in range(len(Q[i]))) row.append(score) scores.append(row) attention_weights = [softmax(row) for row in scores] output = [] for i in range(len(V)): weighted_sum = [sum(attention_weights[i][k] * V[k][j] for k in range(len(V))) for j in range(len(V[0]))] output.append(weighted_sum) return output def multi_head_attention(Q, K, V, num_heads): d_model = len(Q[0]) head_size = d_model // num_heads outputs = [] for head in range(num_heads): q_head = [row[head * head_size:(head + 1) * head_size] for row in Q] k_head = [row[head * head_size:(head + 1) * head_size] for row in K] v_head = [row[head * head_size:(head + 1) * head_size] for row in V] attention_output = self_attention(q_head, k_head, v_head) outputs.extend(attention_output) return outputs def positional_encoding(seq_len, d_model): encoding = [] for pos in range(seq_len): row = [] for i in range(d_model): if i % 2 == 0: row.append(math.sin(pos / (10000 ** (i / d_model)))) else: row.append(math.cos(pos / (10000 ** (i / d_model)))) encoding.append(row) return encoding def add_positional_encoding(embeddings, positional_encodings): return [[val + positional_encodings[i][j] for j, val in enumerate(row)] for i, row in enumerate(embeddings)] def feed_forward_network(x): input_dim = len(x[0]) hidden_dim = 4 output_dim = 2 W1 = [[1 if i == j else 0 for j in range(hidden_dim)] for i in range(input_dim)] b1 = [0] * hidden_dim W2 = [[1 for _ in range(output_dim)] for _ in range(hidden_dim)] b2 = [0] * output_dim hidden = [[max(0, sum(x[i][k] * W1[k][j] for k in range(len(W1))) + b1[j]) for j in range(hidden_dim)] for i in range(len(x))] output = [[sum(hidden[i][k] * W2[k][j] for k in range(len(W2))) + b2[j] for j in range(output_dim)] for i in range(len(hidden))] return output def tokenize(text): return re.sub(r'[.,!?]', '', text.lower()).split() def embed_tokens(tokens): return [[random.random() for _ in range(3)] for _ in tokens] def build_ngram_models(corpus): bigram_model = {} trigram_model = {} words = tokenize(corpus) for i in range(len(words) - 1): word1, word2 = words[i], words[i + 1] if word1 not in bigram_model: bigram_model[word1] = [] bigram_model[word1].append(word2) for i in range(len(words) - 2): word1, word2, word3 = words[i], words[i + 1], words[i + 2] bigram = f"{word1} {word2}" if bigram not in trigram_model: trigram_model[bigram] = [] trigram_model[bigram].append(word3) return {"bigram_model": bigram_model, "trigram_model": trigram_model} def predict_next_word(text, models): bigram_model, trigram_model = models["bigram_model"], models["trigram_model"] words = tokenize(text) if not words: return '' if len(words) == 1: last_word = words[0] if last_word in bigram_model: next_words = bigram_model[last_word] return random.choice(next_words) elif len(words) >= 2: last_bigram = f"{words[-2]} {words[-1]}" if last_bigram in trigram_model: next_words = trigram_model[last_bigram] return random.choice(next_words) elif words[-1] in bigram_model: next_words = bigram_model[words[-1]] return random.choice(next_words) return '' def predict_next_word_with_attention(text, ngram_models): bigram_model, trigram_model = ngram_models["bigram_model"], ngram_models["trigram_model"] tokens = tokenize(text) d_model = 3 embeddings = embed_tokens(tokens) positional_encodings = positional_encoding(len(tokens), d_model) encoded_embeddings = add_positional_encoding(embeddings, positional_encodings) num_heads = 2 attention_output = multi_head_attention(encoded_embeddings, encoded_embeddings, encoded_embeddings, num_heads) ff_output = feed_forward_network(attention_output) ngram_prediction = predict_next_word(text, ngram_models) return ngram_prediction def clean_user_input(text): return re.sub(r'[<>,./;\'"\[\]{}|=_+`~!@#$%^&*()?\-]', '', text).strip().lower() def print_progress(progress, total): percent = (progress / total) * 100 bar_length = 40 filled_length = int(bar_length * progress // total) bar = '=' * filled_length + '-' * (bar_length - filled_length) print(f'\r[{bar}] {percent:.2f}% Complete', end='') def train_model(corpus): print('\nTraining for ' + ModelName + ' has begun.') cleaned_corpus = re.sub(r'[\r\n]+', ' ', corpus.strip()) print_progress(0, 3) cleaned_corpus = re.sub(r'[.,!?]', '', cleaned_corpus) print_progress(1, 3) ngram_models = build_ngram_models(cleaned_corpus) print_progress(2, 3) print_progress(3, 3) print('\nTraining complete.') return ngram_models def correct_text(text): text = text.strip() text = text[0].upper() + text[1:] if not re.search(r'[.!?]$', text): if re.search(r'\b(?:how|when|what|why|where|who|is|are|can|do|does|will|shall)\b', text, re.IGNORECASE): text += '?' else: text += '.' text = re.sub(r'(?<=\.\s)(\w)', lambda x: x.group().upper(), text) text = re.sub(r'\bi\b', 'I', text) text = re.sub(r'\b(i\'m|i\'ve|i\'d|i\'ll)\b', lambda x: x.group().capitalize(), text) return text def is_sentence_complete(sentence, corpus): sentence = sentence.strip() if len(sentence) == 0: return False if 'eos' in sentence.lower() or '' in sentence.lower(): return True return False def predict_sentence_with_attention(input_text, ngram_models, output_length, creativity, recent_history_length=3): cleaned_input = clean_user_input(input_text) sentence = cleaned_input recent_history = [] for _ in range(output_length): prediction = predict_next_word_with_attention(sentence, ngram_models) if not prediction: break if prediction in recent_history: continue recent_history.append(prediction) if len(recent_history) > recent_history_length: recent_history.pop(0) if random.random() < creativity: sentence += ' ' + prediction else: next_words = ngram_models["bigram_model"].get(sentence.split()[-1], []) if next_words: most_likely_word = max(set(next_words), key=next_words.count) sentence += ' ' + most_likely_word if is_sentence_complete(sentence, corpus): break sentence = correct_text(sentence) if cleaned_input in sentence: sentence = sentence.replace(cleaned_input, '', 1).strip() return sentence ngram_models = train_model(corpus) while True: input_text = input('Type a message: ').strip() if input_text.lower() == 'exit': break predicted_sentence = predict_sentence_with_attention(input_text, ngram_models, output_length, creativity) predicted_sentence = predicted_sentence.replace('{name}', f'{ModelName}').strip() predicted_sentence = predicted_sentence.replace('{username}', f'{UserName}').strip() predicted_sentence = predicted_sentence.replace('', '').strip() print(f'{ModelName}:', predicted_sentence)