The disconnect between tokenizer creation and model training in language models allows for specific inputs, such as the infamous SolidGoldMagikarp token, to induce unwanted model behaviour. Although such `glitch tokens', tokens present in the tokenizer vocabulary but that are nearly or entirely absent during model training, have been observed across various models, a reliable method to identify and address them has been missing. We present a comprehensive analysis of Large Language Model toke...| arXiv.org
The development of large language models (LLMs) has expanded to multi-modal systems capable of processing text, images, and speech within a unified framework. Training these models demands significantly larger datasets and computational resources compared to text-only LLMs. To address the scaling challenges, we introduce Mixture-of-Transformers (MoT), a sparse multi-modal transformer architecture that significantly reduces pretraining computational costs. MoT decouples non-embedding parameter...| arXiv.org
1 Introduction| arxiv.org
Due to the compelling improvements brought by BERT, many recent representation models adopted the Transformer architecture as their main building block, consequently inheriting the wordpiece tokenization system despite it not being intrinsically linked to the notion of Transformers. While this system is thought to achieve a good balance between the flexibility of characters and the efficiency of full words, using predefined wordpiece vocabularies from the general domain is not always suitable...| arXiv.org
Autoregressive transformers are spectacular models for short sequences but scale poorly to long sequences such as high-resolution images, podcasts, code, or books. We proposed Megabyte, a multi-scale decoder architecture that enables end-to-end differentiable modeling of sequences of over one million bytes. Megabyte segments sequences into patches and uses a local submodel within patches and a global model between patches. This enables sub-quadratic self-attention, much larger feedforward lay...| arXiv.org
Transformer architectures have led to remarkable progress in many state-of-art applications. However, despite their successes, modern transformers rely on the self-attention mechanism, whose time- ...| PMLR
Introducing EvaByte, an efficient and strong byte-level language model| hkunlp.github.io
With the success of language pretraining, it is highly desirable to develop more efficient architectures of good scalability that can exploit the abundant unlabeled data at a lower cost. To improve the efficiency, we examine the much-overlooked redundancy in maintaining a full-length token-level presentation, especially for tasks that only require a single-vector presentation of the sequence. With this intuition, we propose Funnel-Transformer which gradually compresses the sequence of hidden ...| arXiv.org
1 Introduction| arxiv.org
This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. The approach is demonstrated for text (where the data are discrete) and online handwriting (where the data are real-valued). It is then extended to handwriting synthesis by allowing the network to condition its predictions on a text sequence. The resulting system is able to generate highly realistic cursive ha...| arXiv.org
Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. In this work, we introduce BAGEL, an open-source foundational model that natively supports multimodal understanding and generation. BAGEL is a unified, decoder-only model pretrained on trillions of tokens curated from large-scale interleaved text, image, video, and web data. When scaled with such diverse multimodal interleaved data, BAGEL exhibits emerging capabilities in co...| arXiv.org
Genomic (DNA) sequences encode an enormous amount of information for gene regulation and protein synthesis. Similar to natural language models, researchers have proposed foundation models in genomics to learn generalizable features from unlabeled genome data that can then be fine-tuned for downstream tasks such as identifying regulatory elements. Due to the quadratic scaling of attention, previous Transformer-based genomic models have used 512 to 4k tokens as context (<0.001% of the human gen...| arXiv.org
1 Introduction| arxiv.org
In my last post, I briefly discussed the infuriating fact that a neural network, even when deeply flawed, will often “work” in the sense that it’ll do above-random at classification or a generative network might create things that may sometimes look plausibly from the dataset. | Non_Interactive - Software & ML
State-of-the-art models in natural language processing rely on separate rigid subword tokenization algorithms, which limit their generalization ability and adaptation to new settings. In this paper, we propose a new model inductive bias that learns a subword tokenization end-to-end as part of the model. To this end, we introduce a soft gradient-based subword tokenization module (GBST) that automatically learns latent subword representations from characters in a data-driven fashion. Concretely...| arXiv.org
1 Introduction| arxiv.org
Recent language models have shown impressive multilingual performance, even when not explicitly trained for it. Despite this, there are concerns about the quality of their outputs across different languages. In this paper, we show how disparity in the treatment of different languages arises at the tokenization stage, well before a model is even invoked. The same text translated into different languages can have drastically different tokenization lengths, with differences up to 15 times in som...| arXiv.org
Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments of tokens. Nevertheless, natural units of meaning, such as words or phrases, display varying sizes. To address this mismatch, we equip language models with a dynamic-pooling mechanism, which predicts segment boundaries in an autoregressive fashion. We comp...| arXiv.org
I don’t read as many papers as I once did. I find this surprising as I always assumed that when I made ML my full-time job, I would spend a lot more time reading up on all of the things that other folks in the field are up to.| Non_Interactive - Software & ML
Pipelined NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step. While recent tokenization approaches based on data-derived subword lexicons are less brittle than manually engineered tokenizers, these techniques are not equally suited to all languages, and the use of any fixed vocabulary may limit a model's ability to adapt. In this paper, we present CANINE, a neural encoder that operates directl...| arXiv.org
After spending a lot of time with language models, I have come to the conclusion that tokenization in general is insane and it is a miracle that language models learn anything at all. To drill down into one specific example of silliness which has been bothering me recently, let’s look...| www.beren.io
Token-free language models learn directly from raw bytes and remove the inductive bias of subword tokenization. Operating on bytes, however, results in significantly longer sequences. In this setting, standard autoregressive Transformers scale poorly as the effective memory required grows with sequence length. The recent development of the Mamba state space model (SSM) offers an appealing alternative approach with a fixed-sized memory state and efficient decoding. We propose MambaByte, a toke...| arXiv.org
We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up the training by using a single multiscale spectrogram adversary that efficiently reduces artifacts and produce high-quality samples. We introduce a novel loss balancer mechanism to stabilize training: the weight of a loss now defines the fraction of the ov...| arXiv.org
Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, o...| PMLR
There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and out...| arXiv.org
The assumption across nearly all language model (LM) tokenization schemes is that tokens should be subwords, i.e., contained within word boundaries. While providing a seemingly reasonable inductive bias, is this common practice limiting the potential of modern LMs? Whitespace is not a reliable delimiter of meaning, as evidenced by multi-word expressions (e.g., "by the way"), crosslingual variation in the number of words needed to express a concept (e.g., "spacesuit helmet" in German is "rauma...| arXiv.org
In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable models have been shown to learn nontrivial representations of speech, applicable to unsupervised voice conversion and reaching state-of-the-art performance on unit discovery tasks. For unsupervised representation learning, they became viable alternatives to continuous latent variable models such as the Va...| arXiv.org
I apply recent work on "learning to think" (2015) and on PowerPlay (2011) to the incremental training of an increasingly general problem solver, continually learning to solve new tasks without forgetting previous skills. The problem solver is a single recurrent neural network (or similar general purpose computer) called ONE. ONE is unusual in the sense that it is trained in various ways, e.g., by black box optimization / reinforcement learning / artificial evolution as well as supervised / un...| arXiv.org
Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing demand for high-performance, open-source video tokenizers as video-centric research gains prominence. We introduce VidTok, a versatile video tokenizer that delivers state-of-the-art performance in both continuous and discrete tokenizations. VidTok incorporate...| arXiv.org
Tokenization, the division of input text into input tokens, is an often overlooked aspect of the large language model (LLM) pipeline and could be the source of useful or harmful inductive biases. Historically, LLMs have relied on byte pair encoding, without care to specific input domains. With the increased use of LLMs for reasoning, various number-specific tokenization schemes have been adopted, with popular models like LLaMa and PaLM opting for single-digit tokenization while GPT-3.5 and GP...| arXiv.org
The recent success of Large Language Models (LLMs) has been predominantly driven by curating the training dataset composition, scaling of model architectures and dataset sizes and advancements in pretraining objectives, leaving tokenizer influence as a blind spot. Shedding light on this underexplored area, we conduct a comprehensive study on the influence of tokenizer choice on LLM downstream performance by training 24 mono- and multilingual LLMs at a 2.6B parameter scale, ablating different ...| arXiv.org
We present a literature and empirical survey that critically assesses the state of the art in character-level modeling for machine translation (MT). Despite evidence in the literature that character-level systems are comparable with subword systems, they are virtually never used in competitive setups in WMT competitions. We empirically show that even with recent modeling innovations in character-level natural language processing, character-level MT systems still struggle to match their subwor...| arXiv.org
2 Related work| arxiv.org
We’re on a journey to advance and democratize artificial intelligence through open source and open science.| huggingface.co
LSTMs and other RNN variants have shown strong performance on character-level language modeling. These models are typically trained using truncated backpropagation through time, and it is common to assume that their success stems from their ability to remember long-term contexts. In this paper, we show that a deep (64-layer) transformer model with fixed context outperforms RNN variants by a large margin, achieving state of the art on two popular benchmarks: 1.13 bits per character on text8 an...| arXiv.org
TL;DR: We introduce lookahead decoding, a new, exact, and parallel decoding algorithm to accelerate LLM inference. Look...| lmsys.org
A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies. Although conventional models including RNNs, CNNs, and Transformers have specialized variants for capturing long dependencies, they still struggle to scale to very long sequences of $10000$ or more steps. A promising recent approach proposed modeling sequences by simulating the fundamental state space model (...| arXiv.org
Models that rely on subword tokenization have significant drawbacks, such as sensitivity to character-level noise like spelling errors and inconsistent compression rates across different languages and scripts. While character- or byte-level models like ByT5 attempt to address these concerns, they have not gained widespread adoption -- processing raw byte streams without tokenization results in significantly longer sequence lengths, making training and inference inefficient. This work introduc...| arXiv.org
We describe a simple neural language model that relies only on character-level inputs. Predictions are still made at the word-level. Our model employs a convolutional neural network (CNN) and a highway network over characters, whose output is given to a long short-term memory (LSTM) recurrent neural network language model (RNN-LM). On the English Penn Treebank the model is on par with the existing state-of-the-art despite having 60% fewer parameters. On languages with rich morphology (Arabic,...| arXiv.org
Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low arithmetic intensity of small-batch inference by improving upon previous work in speculative decoding. First, we restructure the speculative batch as a tree, which reduces generation costs and increases the expected tokens per batch. Second, we add a second stage of...| arXiv.org
1 Introduction| arxiv.org
Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as each step necessitates moving the full model parameters from High-Bandwidth Memory (HBM) to the accelerator's cache. While methods such as speculative decoding have been suggested to address this issue, their implementation is impeded by the challenges associated with acquiring and maintaining a separate draft mode...| arXiv.org
We present Chameleon, a family of early-fusion token-based mixed-modal models capable of understanding and generating images and text in any arbitrary sequence. We outline a stable training approach from inception, an alignment recipe, and an architectural parameterization tailored for the early-fusion, token-based, mixed-modal setting. The models are evaluated on a comprehensive range of tasks, including visual question answering, image captioning, text generation, image generation, and long...| arXiv.org
3.2.1 Scaled Dot-Product Attention| arxiv.org
Tokenization is widely used in large language models because it significantly improves performance. However, tokenization imposes several disadvantages, such as performance biases, increased adversarial vulnerability, decreased character-level modeling performance, and increased modeling complexity. To address these disadvantages without sacrificing performance, we propose SpaceByte, a novel byte-level decoder architecture that closes the performance gap between byte-level and subword autoreg...| arXiv.org
We’re on a journey to advance and democratize artificial intelligence through open source and open science.| huggingface.co
Just over a year ago, I wrote about how integer tokenization using the GPT2 and GPT3 tokenizer was insane. This was because that it failed to create a coherent number representation in token space since large numbers of integers were assigned a single unique token, and even multi-token integers were...| www.beren.io
Transformer models yield impressive results on many NLP and sequence modeling tasks. Remarkably, Transformers can handle long sequences which allows them to produce long coherent outputs: full paragraphs produced by GPT-3 or well-structured images produced by DALL-E. These large language models are impressive but also very inefficient and costly, which limits their applications and accessibility. We postulate that having an explicit hierarchical architecture is the key to Transformers that ef...| arXiv.org
Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. By comparison, token-free models that operate directly on raw text (bytes or characters) have many benefits: they can process text in any language out of the box, they are more robust to noise, and they minimize technical debt by removing complex and error-prone text preprocessing pipelines. Since byte or character sequences are longer than token sequences, past work on token-fr...| arXiv.org
Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki. Findings of the Association for Computational Linguistics: EMNLP 2020. 2020.| ACL Anthology
Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.| ACL Anthology
Character-level language models obviate the need for separately trained tokenizers, but efficiency suffers from longer sequence lengths. Learning to combine character representations into tokens has made training these models more efficient, but they still require decoding characters individually. We propose Toucan, an augmentation to character-level models to make them "token-aware". Comparing our method to prior work, we demonstrate significant speed-ups in character generation without a lo...| arXiv.org
Musings of a Computer Scientist.| karpathy.github.io
We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget. We find that current large language models are significantly undertrained, a consequence of the recent focus on scaling language models whilst keeping the amount of training data constant. By training over 400 language models ranging from 70 million to over 16 billion parameters on 5 to 500 billion tokens, we find that for compute-optimal training, the model size ...| arXiv.org
We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and the amount of compute used for training, with some trends spanning more than seven orders of magnitude. Other architectural details such as network width or depth have minimal effects within a wide range. Simple equations govern the dependence of overfitting on model/dataset size and the dependence of training speed on model size. These re...| arXiv.org