Nano-BERT is a straightforward, lightweight and comprehensible custom implementation of BERT, inspired by the foundational "Attention is All You Need" paper. The primary objective of this project is to distill the essence of transformers by simplifying the complexities and unnecessary details.
☆21Oct 19, 2023Updated 3 years ago
Alternatives and similar repositories for nano-BERT
Users that are interested in nano-BERT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An implementation of PSGD Kron in JAX for distributed training in JAX or Flax☆10Nov 6, 2025Updated last year
- 微调阿里开源的文字检测模型，利用合合识别返回的OCR结果作为初始训练数据，对模型进行优化训练，使其更加适应1万张图片的具体场景，提高文字识别的精度。☆10Dec 9, 2024Updated last year
- ☆10Apr 19, 2026Updated 6 months ago
- ☆15Jun 29, 2026Updated 4 months ago
- Introductory lecture on Pytorch☆10May 8, 2022Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Word Embeddings for Low Resource Languages: The Case of Buryat☆10Mar 12, 2025Updated last year
- ☆15Jun 24, 2025Updated last year
- ☆17Oct 11, 2023Updated 3 years ago
- Predicting water moelcule placements on protein surfaces using flow matching conditioned on learned protein structure embeddings.☆18Sep 17, 2026Updated last month
- A scalable architecture for generating 3D molecules atom-by-atom☆15Sep 6, 2025Updated last year
- Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference☆16Oct 21, 2026Updated 2 weeks ago
- The Polaris datasets and benchmarks recipes☆16May 26, 2025Updated last year
- ☆13Jul 1, 2025Updated last year
- An implementation of the Equivariant Graph Neural Network (EGNN) layer type for DGL-PyTorch.☆15Dec 27, 2022Updated 3 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆13Oct 15, 2023Updated 3 years ago
- A simple, easy-to-hack GraphRAG implementation☆15Sep 21, 2024Updated 2 years ago
- A *minimal* protein structure predictor written in ~200 lines of *readable* PyTorch.☆23Oct 16, 2026Updated 3 weeks ago
- ☆17Oct 8, 2026Updated 3 weeks ago
- Batched optimisation algorithms for neural network potential driven molecular dynamics.☆17Nov 27, 2025Updated 11 months ago
- ☆14Jul 24, 2025Updated last year
- CASP15 performance benchmarking of the state-of-the-art protein structure prediction methods☆16Dec 13, 2023Updated 2 years ago
- 非官方的MDCSpell论文的实现☆18Oct 16, 2022Updated 4 years ago
- Interactive ML Toolset☆17Jun 17, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A custom Huggingface trainer which supports logging auxiliary losses returned by your model☆15Jul 27, 2025Updated last year
- Improving Neural Text Generation with Reinforcement Learning☆23Jan 13, 2021Updated 5 years ago
- The source code used for paper "Unsupervised Key Event Detection from Massive Text Corpora", published in KDD 2022.☆21Jul 15, 2023Updated 3 years ago
- MLX implementation of Meta's ESM-1 protein language model☆21Apr 17, 2024Updated 2 years ago
- ☆20Dec 5, 2025Updated 11 months ago
- Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensembles☆23May 16, 2026Updated 5 months ago
- Jax / Haiku implementation of DimeNet++.☆18Mar 31, 2022Updated 4 years ago
- [Nature Communications] The implementation for the paper "An equivariant pretrained transformer for unified 3D molecular representation l…☆18Jun 25, 2026Updated 4 months ago
- SIMD instructions for faster distance calculations.☆26Apr 7, 2026Updated 7 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Training hybrid models for dummies.☆30Nov 1, 2025Updated last year
- Gradio Client in Rust.☆31Sep 8, 2026Updated last month
- [ICML'25] The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products☆20Jul 16, 2025Updated last year
- (ICML 2026 Oral) Protein Autoregressive Modeling via Multiscale Structure Generation, Official Implementation from ByteDance Seed☆21Jul 3, 2026Updated 4 months ago
- Fully-Differentiable Tensor Spherical Harmonics in JAX☆21Apr 11, 2026Updated 6 months ago
- Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding (Findings of EMNLP'23)☆11Aug 24, 2024Updated 2 years ago
- ☆32Oct 26, 2026Updated last week