Nobody owns this listing yet

KerasFormers is live in the directory, but no verified owner controls the page.

Claim this listing
  • Pick your launch daySchedule a launch and compete for the daily #1 spot.
  • Win trophies you can embedRank top 3 on launch day and get an embeddable trophy.
  • “Featured on AI Kaptan” badgeOwner-only badge with your live upvote count.
  • Control what the page saysEdit copy, pricing, links and screenshots as the owner.

Unclaimed listings don't stay up forever. Listings left unclaimed are removed from the directory in periodic cleanups. When a listing goes, it goes everywhere — the tool page and every alternatives comparison it appears on, along with the rankings and backlinks that page had built up.

Verify with a work email on the domain (about 2 minutes), then a one-time $5 listing fee. See everything you get

Scheduled launch — Aug 23, 2026

KerasFormers is listed on AI Kaptan and will enter the daily launch competition on that day. Community upvotes open on launch day.

KerasFormers
Developer Tools
Free

KerasFormers

Open-source Keras 3 collection of pretrained transformer models across Vision, LLMs, VLMs, Depth, and Speech running on JAX, PyTorch, and TensorFlow.

Rating
0
Reviews
0
Upvotes
about 3 hours ago
Listed
Developer Tools
Artificial Intelligence
GitHub
Keras 3
Pretrained Models
Deep Learning
Machine Learning
PyTorch
TensorFlow
JAX
Tool information
Provider
IMvision12
Platforms
Linux
macOS
Windows
Languages
Python
Added to directory
about 3 hours ago
Last updated
about 3 hours ago
Rating
Not available
Pricing
Free

About KerasFormers

What the tool does and who it's for

KerasFormers is an open-source Keras 3 collection of pretrained transformer and deep learning models designed to run seamlessly across JAX, PyTorch, and TensorFlow backends. It provides standardized multi-backend implementations for a wide spectrum of machine learning tasks, including computer vision (image classification, object detection, segmentation, and depth estimation), large language models (LLMs), vision-language models (VLMs), speech recognition, and text encoding. By implementing models natively in pure Keras 3, KerasFormers allows developers and researchers to use a single code implementation without backend-specific lock-in.

Key capabilities

Pure Keras 3 multi-backend support, executing identically across PyTorch, JAX, and TensorFlow.
Comprehensive Vision architecture collection including classification, detection (DETR, RT-DETR), and segmentation (SAM, SegFormer).
Extensive Large Language Model (LLM) support covering Llama, Gemma, Qwen, Mistral, and DeepSeek variants.
Vision-Language Models (VLMs) and grounding tools like CLIP, SigLIP, Qwen2-VL, and LocateAnything.
Monocular Depth Estimation models including Depth Anything V1 and V2.
Speech recognition and audio-language support, including Whisper and Speech2Text.
Text encoding and masked language models including BERT, RoBERTa, and DeBERTa.
Standardized weight loading from Hugging Face Hub with modular task heads.

Pricing

Free — plans below

Open Source

Most popular

Free

  • Full access to model implementations
  • Multi-backend execution (JAX, PyTorch, TensorFlow)
  • Open-source GitHub repository
  • Pretrained weights hosted on Hugging Face

Reviews

Be the first to review KerasFormers

No reviews yet

Be the first to share your experience with KerasFormers.

Featured Tools

Handpicked by our team of experts

Suggest an Update

Found outdated information? Help us keep this listing accurate.

FAQ

KerasFormers FAQs

Common questions about KerasFormers