FLAN-T5-XXL Fused Model
This repository contains a fused version of FLAN-T5-XXL, combining the split files available at Google's FLAN-T5-XXL repository. These files have been merged for easier use in AI applications, including image generation models.
Files
flan_t5_xxl_fp32.safetensors: Full-precision FP32 model.flan_t5_xxl_fp16.safetensors: Half-precision FP16 model for memory-efficient inference.
Comparison: FLAN-T5-XXL vs T5-XXL v1.1 on Flux.1[dev] (base model: blue_pencil-flux1_v0.0.1)
Below are example images generated using FLAN-T5-XXL and T5-XXL v1.1 models in Flux.1. FLAN-T5-XXL provides more accurate responses to prompts.
FLAN-T5-XXL Output
T5-XXL v1.1 Output
A detailed comparison is available in this blog post.
License
This model is provided under the Apache 2.0 License.
The uploader does not claim any rights over the model.
Acknowledgments
- Original source: Google's FLAN-T5-XXL repository.
- GGUF version: dumb-dev's Hugging Face repository.
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.