OpenMOSE / RWKV5-LM-LoRA
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.
☆12Updated 10 months ago
Alternatives and similar repositories for RWKV5-LM-LoRA:
Users that are interested in RWKV5-LM-LoRA are comparing it to the libraries listed below
- A large-scale RWKV v6, v7 inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy on docker. Supports tr…☆25Updated last week
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆141Updated 5 months ago
- Reinforcement Learning Toolkit for RWKV.(v6,v7) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the possi…☆24Updated this week
- RWKV-7: Surpassing GPT☆73Updated 2 months ago
- An unsupervised model merging algorithm for Transformers-based language models.☆102Updated 9 months ago
- GoldFinch and other hybrid transformer components☆43Updated 6 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- ☆22Updated 2 months ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆96Updated 4 months ago
- A repository for research on medium sized language models.☆76Updated 8 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆36Updated last year
- ☆33Updated 6 months ago
- ☆14Updated 9 months ago
- entropix style sampling + GUI☆25Updated 3 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆31Updated 5 months ago
- QuIP quantization☆48Updated 10 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆115Updated last year
- ☆31Updated last year
- ☆31Updated 7 months ago
- RWKV, in easy to read code☆62Updated 2 months ago
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- ☆27Updated last year
- State tuning tunes the state☆29Updated 10 months ago
- Triton Implementation of HyperAttention Algorithm☆46Updated last year
- ☆49Updated 10 months ago
- ☆48Updated 2 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated 10 months ago
- Unofficial Implementation of Evolutionary Model Merging☆33Updated 10 months ago
- ☆47Updated 5 months ago