OpenMOSE / RWKV5-LM-LoRALinks
RWKV v5,v6 LoRA Trainer on Cuda and Rocm Platform. RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
☆13Updated last year
Alternatives and similar repositories for RWKV5-LM-LoRA
Users that are interested in RWKV5-LM-LoRA are comparing it to the libraries listed below
Sorting:
- A large-scale RWKV v6, v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to de…☆38Updated 3 weeks ago
- ☆36Updated last month
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated last month
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆32Updated 10 months ago
- RWKV-7: Surpassing GPT☆91Updated 7 months ago
- GoldFinch and other hybrid transformer components☆45Updated 11 months ago
- ☆14Updated last year
- ☆34Updated 11 months ago
- Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton☆33Updated last week
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆44Updated last month
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- RWKV-LM-V7(https://github.com/BlinkDL/RWKV-LM) Under Lightning Framework☆28Updated last week
- QLoRA with Enhanced Multi GPU Support☆37Updated last year
- RWKV centralised docs for the community☆27Updated 2 months ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated 10 months ago
- Merge LLM that are split in to parts☆26Updated last year
- Implementation of a Light Recurrent Unit in Pytorch☆48Updated 8 months ago
- A repository for research on medium sized language models.☆76Updated last year
- This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the …☆51Updated 6 months ago
- ☆129Updated last week
- RWKV, in easy to read code☆72Updated 2 months ago
- ☆49Updated last year
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆16Updated 7 months ago
- Implementation of the Mamba SSM with hf_integration.☆56Updated 9 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 2 weeks ago
- An unsupervised model merging algorithm for Transformers-based language models.☆105Updated last year
- This project is established for real-time training of the RWKV model.☆49Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated last year
- MiSS is a novel PEFT method that features a low-rank structure but introduces a new update mechanism distinct from LoRA, achieving an exc…☆19Updated this week
- ☆35Updated last year