Step 1: Plan and design the LLM

1. Standard model design
2. LLM has the ability to re-train itself, to hit the re-train button. (no human required)
3. LLM is constantly re-working its training data to improve its training data. (no human required)

Note: focus on the LLM's ability to distinguish differences correctly, better from worse, yes from no and so on, successful compile vs errors, red from blue.

Demonstrator must be resource light enough for the LLM to perform these tasks.

Step 2: Eval Space

The tools that give the LLM the ability to test, proof and rework training data. For instance, a code compiler or a training data compiler. A versus B thinking.

Make the LLM

1. Get the training datasets: Sources: Common Crawl, Wikipedia, books, articles, forums, public datasets (e.g., Project Gutenberg).
2. Preprocess dataset: Data Preprocessing
1. Tokenization: Split text into tokens (words, subwords, or characters).
2. Normalization: Lowercase text, remove special characters, handle contractions, etc.
3. Filtering: Remove non-text content, duplicates, and overly long or short texts.
4. Encoding: Convert tokens to numerical representations using a tokenizer.
3. Choose architecture for your LLM. Transformer-based models (e.g., GPT, BERT), Parameters: Define model size (number of layers, heads, hidden units).
4. Training
5. Evaludation

from transformers import GPT2Config, GPT2LMHeadModel, GPT2Tokenizer, Trainer, TrainingArguments, TextDataset, DataCollatorForLanguageModeling

# Define configuration
config = GPT2Config(
    vocab_size=50257,
    n_positions=1024,
    n_ctx=1024,
    n_embd=768,
    n_layer=12,
    n_head=12,
    n_inner=3072,
    activation_function='gelu',
    resid_pdrop=0.1,
    embd_pdrop=0.1,
    attn_pdrop=0.1,
    layer_norm_epsilon=1e-5,
    initializer_range=0.02,
)

# Initialize tokenizer
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
tokenizer.add_special_tokens({'pad_token': '[PAD]'})

# Prepare dataset
def load_dataset(file_path, tokenizer):
    return TextDataset(
        tokenizer=tokenizer,
        file_path=file_path,
        block_size=128,
    )

train_dataset = load_dataset("path/to/train.txt", tokenizer)
val_dataset = load_dataset("path/to/val.txt", tokenizer)
data_collator = DataCollatorForLanguageModeling(
    tokenizer=tokenizer,
    mlm=False,
)

# Initialize model
model = GPT2LMHeadModel(config)
model.resize_token_embeddings(len(tokenizer))

# Set training arguments
training_args = TrainingArguments(
    output_dir="./results",
    overwrite_output_dir=True,
    num_train_epochs=3,
    per_device_train_batch_size=2,
    per_device_eval_batch_size=2,
    save_steps=10_000,
    save_total_limit=2,
    prediction_loss_only=True,
    logging_dir='./logs',
)

# Create trainer and train
trainer = Trainer(
    model=model,
    args=training_args,
    data_collator=data_collator,
    train_dataset=train_dataset,
    eval_dataset=val_dataset,
)

trainer.train()

# Save the model
model.save_pretrained("./trained_model")
tokenizer.save_pretrained("./trained_model")
Copy

another:

import torch

import torch.nn as nn
from transformers import PreTrainedModel, PretrainedConfig, Trainer, TrainingArguments
from datasets import load_dataset
from tokenizers import Tokenizer, models, pre_tokenizers, trainers
from transformers import PreTrainedTokenizerFast

# Define the model architecture
class NewLM(PreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.embedding = nn.Embedding(config.vocab_size, config.hidden_size)
        self.transformer = nn.TransformerEncoder(
            nn.TransformerEncoderLayer(
                d_model=config.hidden_size,
                nhead=config.num_heads,
                dim_feedforward=config.intermediate_size,
                dropout=config.hidden_dropout_prob
            ),
            num_layers=config.num_hidden_layers
        )
        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size)
        
    def forward(self, input_ids, attention_mask=None):
        x = self.embedding(input_ids)
        if attention_mask is not None:
            x = x.permute(1, 0, 2)  # TransformerEncoder expects seq_len first
            x = self.transformer(x, src_key_padding_mask=attention_mask)
            x = x.permute(1, 0, 2)  # Change back to batch first
        else:
            x = x.permute(1, 0, 2)
            x = self.transformer(x)
            x = x.permute(1, 0, 2)
        return self.lm_head(x)

# Create a custom configuration
class NewLMConfig(PretrainedConfig):
    model_type = "new_lm"
    def __init__(
        self,
        vocab_size=30000,
        hidden_size=256,
        num_hidden_layers=6,
        num_heads=8,
        intermediate_size=1024,
        hidden_dropout_prob=0.1,
        max_position_embeddings=512,
        **kwargs
    ):
        super().__init__(**kwargs)
        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_heads = num_heads
        self.intermediate_size = intermediate_size
        self.hidden_dropout_prob = hidden_dropout_prob
        self.max_position_embeddings = max_position_embeddings

# Train tokenizer
def train_tokenizer(texts):
    tokenizer = Tokenizer(models.BPE())
    tokenizer.pre_tokenizer = pre_tokenizers.Whitespace()
    trainer = trainers.BpeTrainer(special_tokens=["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]"])
    tokenizer.train_from_iterator(texts, trainer)
    return PreTrainedTokenizerFast(tokenizer_object=tokenizer)

# Load and preprocess data
dataset = load_dataset("wikitext", "wikitext-2-raw-v1", split="train")
texts = dataset["text"]

# Train tokenizer
tokenizer = train_tokenizer(texts)

# Tokenize dataset
def tokenize_function(examples):
    return tokenizer(examples["text"], truncation=True, max_length=512, padding="max_length")

tokenized_dataset = dataset.map(tokenize_function, batched=True, remove_columns=dataset.column_names)

# Initialize model
config = NewLMConfig(vocab_size=len(tokenizer))
model = NewLM(config)

# Set training arguments
training_args = TrainingArguments(
    output_dir="./results",
    overwrite_output_dir=True,
    num_train_epochs=3,
    per_device_train_batch_size=8,
    save_steps=10_000,
    save_total_limit=2,
    prediction_loss_only=True,
    logging_dir='./logs',
)

# Define data collator
def data_collator(features):
    return {
        "input_ids": torch.stack([torch.tensor(f["input_ids"]) for f in features]),
        "attention_mask": torch.stack([torch.tensor(f["attention_mask"]) for f in features]),
        "labels": torch.stack([torch.tensor(f["input_ids"]) for f in features]),
    }

# Create trainer and train
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_dataset,
    data_collator=data_collator,
)
trainer.train()

# Save the model and tokenizer
model.save_pretrained("./new_lm")
tokenizer.save_pretrained("./new_lm")
Copy