Apple Intelligence Foundation Language Models

• URL: http://arxiv.org/abs/2407.21075v1
• Date: Mon, 29 Jul 2024 18:38:49 GMT
• Title: Apple Intelligence Foundation Language Models
• Abstract summary: This report describes the model architecture, the data used to train the model, the training process, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.
• Score: 109.60033785567484
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

Related papers

• Apple Intelligence Foundation Language Models: Tech Report 2025 [246.04717786298764]
  We introduce two foundation language models that power Apple Intelligence features across Apple devices and services.<n>Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling.<n>A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning.
  arXiv  Detail & Related papers  (2025-07-17T23:37:19Z)
• Command A: An Enterprise-Ready Large Language Model [180.18356391290172]
  Command A is an agent-optimised and multilingual-capable model. It offers best-in-class Retrieval Augmented Generation capabilities.
  arXiv  Detail & Related papers  (2025-04-01T12:08:07Z)
• Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions [65.89403417819764]
  We quantify the impact of design choices on language model capabilities. By incorporating features besides model size and number of training tokens, we can achieve a relative 3-28% increase in ability to predict downstream performance.
  arXiv  Detail & Related papers  (2025-03-05T19:46:04Z)
• What matters when building vision-language models? [52.8539131958858]
  We develop Idefics2, an efficient foundational vision-language model with 8 billion parameters. Idefics2 achieves state-of-the-art performance within its size category across various multimodal benchmarks. We release the model (base, instructed, and chat) along with the datasets created for its training.
  arXiv  Detail & Related papers  (2024-05-03T17:00:00Z)
• Yi: Open Foundation Models by 01.AI [42.94680878285869]
  Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context models, depth-upscaled models, and vision-language models. Our base models achieve strong performance on a wide range of benchmarks like MMLU, and our fine chat models deliver strong human preference rate on major evaluation platforms like AlpacaEval and Arena.
  arXiv  Detail & Related papers  (2024-03-07T16:52:49Z)
• The Case for Co-Designing Model Architectures with Hardware [13.022505733049597]
  We provide a set of guidelines for users to maximize the runtime performance of their transformer models. We find the throughput of models with efficient model shapes is up to 39% higher.
  arXiv  Detail & Related papers  (2024-01-25T19:50:31Z)
• MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain Applications [46.337078949637345]
  We present MindLLM, a novel series of bilingual lightweight large language models, trained from scratch. A thorough account of experiences accrued during large model development is given, covering every step of the process. MindLLM consistently matches or surpasses the performance of other open-source larger models on some public benchmarks.
  arXiv  Detail & Related papers  (2023-10-24T12:22:34Z)
• Model Provenance via Model DNA [23.885185988451667]
  We introduce a novel concept of Model DNA which represents the unique characteristics of a machine learning model. We develop an efficient framework for model provenance identification, which enables us to identify whether a source model is a pre-training model of a target model.
  arXiv  Detail & Related papers  (2023-08-04T03:46:41Z)
• What Language Model to Train if You Have One Million GPU Hours? [54.32062236748831]
  We study the impact of different modeling practices and their impact on zero-shot generalization. We also study the performance of a multilingual model and how it compares to the English-only one. All our models and code are open-sourced at https://huggingface.co/bigscience.
  arXiv  Detail & Related papers  (2022-10-27T13:43:27Z)
• Language Models are General-Purpose Interfaces [109.45478241369655]
  We propose to use language models as a general-purpose interface to various foundation models. A collection of pretrained encoders perceive diverse modalities (such as vision, and language) We propose a semi-causal language modeling objective to jointly pretrain the interface and the modular encoders.
  arXiv  Detail & Related papers  (2022-06-13T17:34:22Z)
• METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals [151.3601429216877]
  We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model. We propose a recipe, namely "Model generated dEnoising TRaining Objective" (METRO) The resultant models, METRO-LM, consisting of up to 5.4 billion parameters, achieve new state-of-the-art on the GLUE, SuperGLUE, and SQuAD benchmarks.
  arXiv  Detail & Related papers  (2022-04-13T21:39:15Z)
• What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization? [50.84738303888189]
  We present a large-scale evaluation of modeling choices and their impact on zero-shot generalization. We train models with over 5 billion parameters for more than 170 billion tokens. We find that pretrained causal decoder models can be efficiently adapted into non-causal decoder models.
  arXiv  Detail & Related papers  (2022-04-12T14:19:49Z)
• ANNA: Enhanced Language Representation for Question Answering [5.713808202873983]
  We show how approaches affect performance individually and that the approaches are jointly considered in pre-training models. We propose an extended pre-training task, and a new neighbor-aware mechanism that attends neighboring tokens more to capture the richness of context for pre-training language modeling. Our best model achieves new state-of-the-art results of 95.7% F1 and 90.6% EM on SQuAD 1.1 and also outperforms existing pre-trained language models such as RoBERTa, ALBERT, ELECTRA, and XLNet.
  arXiv  Detail & Related papers  (2022-03-28T05:26:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.