CivArchive
    T5 - v1.1 XXL
    Preview 135265728

    Google's T5

    Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new “Colossal Clean Crawled Corpus”, we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code.

    https://huggingface.co/google/t5-v1_1-xxl

    Description

    T5 Version 1.1 includes the following improvements compared to the original T5 model- GEGLU activation in feed-forward hidden layer, rather than ReLU - see here.

    • Dropout was turned off in pre-training (quality win). Dropout should be re-enabled during fine-tuning.

    • Pre-trained on C4 only without mixing in the downstream tasks.

    • no parameter sharing between embedding and classifier layer

    • "xl" and "xxl" replace "3B" and "11B". The model shapes are a bit different - larger d_model and smaller num_heads and d_ff.

    Note: T5 Version 1.1 was only pre-trained on C4 excluding any supervised training. Therefore, this model has to be fine-tuned before it is useable on a downstream task. Pretraining Dataset: C4

    Other Community Checkpoints: here

    Paper: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

    Authors: Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu

    TextEncoder
    Other
    by CivitaiOfficial
    Download (Beta) View on CivitAI
    base model

    Details

    Downloads
    6
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/9/2026
    Updated
    7/11/2026
    Deleted
    -

    Files

    t5_v11XXL.safetensors

    Size:
    9.12 GB
    SHA256:
    6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635

    Mirrors

    HuggingFace (207 mirrors)
    CivitAI (6 mirrors)
    CivitasBay (1 mirrors)
    ModelScope (2 mirrors)
    ModelScope CN (2 mirrors)
    ShakkerAI (1 mirrors)

    t5_v11XXL.safetensors

    Size:
    4.80 GB
    SHA256:
    a498f0485dc9536735258018417c3fd7758dc3bccc0a645feaa472b34955557a

    Mirrors

    HuggingFace (68 mirrors)
    CivitAI (2 mirrors)
    ModelScope (1 mirrors)

    t5_v11XXL.safetensors

    Size:
    4.56 GB
    SHA256:
    7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09

    Mirrors

    HuggingFace (201 mirrors)
    CivitAI (5 mirrors)
    CivitasBay (1 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (3 mirrors)