sanderwood / bgptLinks
Beyond Language Models: Byte Models are Digital World Simulators
☆328Updated last year
Alternatives and similar repositories for bgpt
Users that are interested in bgpt are comparing it to the libraries listed below
Sorting:
- PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention…☆291Updated last year
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆346Updated 8 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆200Updated last year
- ☆194Updated 3 weeks ago
- Reference implementation of Megalodon 7B model☆524Updated 3 months ago
- RWKV in nanoGPT style☆192Updated last year
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction☆388Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated 10 months ago
- GRadient-INformed MoE☆264Updated 11 months ago
- Implementation of DoRA☆301Updated last year
- Embed arbitrary modalities (images, audio, documents, etc) into large language models.☆186Updated last year
- Micro Llama is a small Llama based model with 300M parameters trained from scratch with $500 budget☆158Updated 3 weeks ago
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆158Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- [ICML 2024] CLLMs: Consistency Large Language Models☆401Updated 9 months ago
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆161Updated 4 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆559Updated 8 months ago
- ☆202Updated 8 months ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆244Updated last year
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆434Updated 3 months ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆223Updated last year
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆206Updated last year
- [NeurIPS'24] SelfCodeAlign: Self-Alignment for Code Generation☆309Updated 6 months ago
- X-LoRA: Mixture of LoRA Experts☆236Updated last year
- [ACL 2024] Progressive LLaMA with Block Expansion.☆509Updated last year
- ☆311Updated last year
- A bagel, with everything.☆324Updated last year
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆227Updated 3 months ago
- Pre-training code for Amber 7B LLM☆167Updated last year
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆245Updated 7 months ago