ofirpress / attention_with_linear_biasesLinks
Code for the ALiBi method for transformer language models (ICLR 2022)
☆547Updated 2 years ago
Alternatives and similar repositories for attention_with_linear_biases
Users that are interested in attention_with_linear_biases are comparing it to the libraries listed below
Sorting:
- Sequence modeling with Mega.☆302Updated 2 years ago
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆654Updated last year
- Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"☆457Updated 2 years ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆231Updated last year
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆876Updated 2 years ago
- Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint☆422Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆375Updated last year
- Recurrent Memory Transformer☆154Updated 2 years ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆421Updated last year
- Root Mean Square Layer Normalization☆261Updated 2 years ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆788Updated 5 months ago
- Rectified Rotary Position Embeddings☆385Updated last year
- An implementation of local windowed attention for language modeling☆492Updated 5 months ago
- [NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation☆474Updated last year
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆389Updated 2 years ago
- Long Range Arena for Benchmarking Efficient Transformers☆772Updated 2 years ago
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆840Updated 2 years ago
- Automatically split your PyTorch models on multiple GPUs for training & inference☆657Updated 2 years ago
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆371Updated 2 years ago
- Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent,…☆227Updated last year
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆638Updated 2 years ago
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆473Updated last year
- An implementation of masked language modeling for Pytorch, made as concise and simple as possible☆179Updated 2 years ago
- Research code for pixel-based encoders of language (PIXEL)☆345Updated 5 months ago
- Scaling Data-Constrained Language Models☆343Updated 6 months ago
- Large Context Attention☆759Updated 3 months ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆224Updated last year
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆410Updated last year
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆383Updated last year
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)☆464Updated 3 years ago