PicoCreator / RWKV-LM-LoRA
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.
☆10Updated last year
Alternatives and similar repositories for RWKV-LM-LoRA:
Users that are interested in RWKV-LM-LoRA are comparing it to the libraries listed below
- Script and instruction how to fine-tune large RWKV model on your data for Alpaca dataset☆31Updated last year
- ☆14Updated 10 months ago
- Experimental sampler to make LLMs more creative☆30Updated last year
- Modified Beam Search with periodical restart☆12Updated 5 months ago
- RWKV centralised docs for the community☆20Updated last month
- ☆27Updated last year
- entropix style sampling + GUI☆25Updated 3 months ago
- ☆20Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- 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 …☆12Updated 10 months ago
- ☆12Updated last year
- Merge LLM that are split in to parts☆26Updated last year
- Trying to deconstruct RWKV in understandable terms☆14Updated last year
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated last year
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆41Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated 11 months ago
- Running Microsoft's BitNet via Electron, React & Astro☆18Updated 3 months ago
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆31Updated this week
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- A large-scale RWKV v6, v7(World, ARWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy on docke…☆30Updated this week
- Run ONNX RWKV-v4 models with GPU acceleration using DirectML [Windows], or just on CPU [Windows AND Linux]; Limited to 430M model at this…☆20Updated last year
- Easily deploy your rwkv model☆18Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated 9 months ago
- ToK aka Tree of Knowledge for Large Language Models LLM. It's a novel dataset that inspires knowledge symbolic correlation in simple inpu…☆51Updated last year
- This project is established for real-time training of the RWKV model.☆49Updated 9 months ago
- ☆42Updated last year
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆15Updated 3 months ago