dingo-actual / infini-transformerLinks
PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)
β290Updated last year
Alternatives and similar repositories for infini-transformer
Users that are interested in infini-transformer are comparing it to the libraries listed below
Sorting:
- Unofficial PyTorch/π€Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Iβ¦β367Updated last year
- Beyond Language Models: Byte Models are Digital World Simulatorsβ325Updated last year
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsβ¦β342Updated 7 months ago
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)β160Updated 3 months ago
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Modelsβ226Updated 3 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.β198Updated last year
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"β555Updated 7 months ago
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reductionβ388Updated last year
- Some preliminary explorations of Mamba's context scaling.β216Updated last year
- Implementation of DoRAβ299Updated last year
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ532Updated 2 months ago
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ397Updated 8 months ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793β431Updated 2 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.β739Updated 10 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"β244Updated 6 months ago
- A family of compressed models obtained via pruning and knowledge distillationβ347Updated 8 months ago
- Official PyTorch implementation of QA-LoRAβ138Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"β154Updated 9 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)β205Updated last year
- β199Updated 7 months ago
- Implementation of π₯₯ Coconut, Chain of Continuous Thought, in Pytorchβ178Updated last month
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"β167Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAIβ288Updated 2 months ago
- Multipack distributed sampler for fast padding-free training of LLMsβ199Updated 11 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024β323Updated 3 months ago
- β192Updated last week
- Normalized Transformer (nGPT)β185Updated 8 months ago
- BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.β208Updated 2 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"β238Updated last month
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.β237Updated 11 months ago