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:
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated last year
- A large-scale RWKV v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy…☆43Updated last week
- RWKV-7: Surpassing GPT☆95Updated 9 months ago
- Fast modular code to create and train cutting edge LLMs☆68Updated last year
- RWKV centralised docs for the community☆29Updated last month
- An unsupervised model merging algorithm for Transformers-based language models.☆107Updated last year
- RWKV, in easy to read code☆71Updated 5 months ago
- ☆144Updated 3 weeks ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆200Updated last year
- Fast, Modern, and Low Precision PyTorch Optimizers☆109Updated last week
- Evaluating LLMs with Dynamic Data☆91Updated last month
- Low-Rank adapter extraction for fine-tuned transformers models☆176Updated last year
- State tuning tunes the state☆35Updated 7 months ago
- ☆38Updated 4 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated 11 months ago
- ☆17Updated 8 months ago
- ☆134Updated last year
- RWKV in nanoGPT style☆193Updated last year
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆65Updated last year
- Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.☆73Updated 7 months ago
- ☆34Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- ☆49Updated last year
- ☆81Updated last year
- This project is established for real-time training of the RWKV model.☆50Updated last year
- QuIP quantization☆59Updated last year
- A fast RWKV Tokenizer written in Rust☆53Updated last month
- QLoRA with Enhanced Multi GPU Support☆37Updated 2 years ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 4 months ago
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆53Updated 3 weeks ago