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
Related projects ⓘ
Alternatives and complementary repositories for RWKV-LM-LoRA
- ☆14Updated 7 months ago
- Script and instruction how to fine-tune large RWKV model on your data for Alpaca dataset☆31Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 8 months ago
- RWKV centralised docs for the community☆19Updated 2 months ago
- Modified Beam Search with periodical restart☆12Updated 2 months ago
- ☆20Updated last year
- entropix style sampling + GUI☆25Updated 3 weeks ago
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated last year
- ☆27Updated last year
- Using multiple LLMs for ensemble Forecasting☆16Updated 10 months ago
- Using open source LLMs to build synthetic datasets for direct preference optimization☆40Updated 8 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated 8 months ago
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆15Updated last week
- ☆41Updated 2 weeks ago
- 🚀 Automatically convert unstructured data into a high-quality 'textbook' format, optimized for fine-tuning Large Language Models (LLMs)☆25Updated last year
- RWKV-7: Surpassing GPT☆45Updated this week
- [WIP] Transformer to embed Danbooru labelsets☆13Updated 7 months ago
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- GoldFinch and other hybrid transformer components☆39Updated 4 months ago
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- An experiment to see if chatgpt can improve the output of the stanford alpaca dataset☆12Updated last year
- Reinforcement Learning Toolkit for RWKV. Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning Let's boost the model's int…☆19Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 7 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- QLoRA for Masked Language Modeling☆20Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated 6 months ago
- 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
- Experimental sampler to make LLMs more creative☆30Updated last year