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.
☆9Updated 10 months ago
Related projects: ⓘ
- Script and instruction how to fine-tune large RWKV model on your data for Alpaca dataset☆31Updated last year
- ☆14Updated 5 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
- RWKV centralised docs for the community☆19Updated 2 weeks ago
- Trying to deconstruct RWKV in understandable terms☆14Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated last year
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆22Updated 6 months ago
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- Modified Beam Search with periodical restart☆12Updated last week
- ☆13Updated last year
- ☆26Updated last year
- 🚀 Automatically convert unstructured data into a high-quality 'textbook' format, optimized for fine-tuning Large Language Models (LLMs)☆24Updated 11 months ago
- Easily deploy your rwkv model☆18Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 6 months ago
- Using open source LLMs to build synthetic datasets for direct preference optimization☆33Updated 6 months ago
- Experimental sampler to make LLMs more creative☆29Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆67Updated last year
- ☆33Updated last month
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆40Updated last year
- ☆25Updated 6 months ago
- Finetune any model on HF in less than 30 seconds☆56Updated last week
- An OpenAI API compatible LLM inference server based on ExLlamaV2.☆21Updated 7 months ago
- ☆20Updated 11 months ago
- An experiment to see if chatgpt can improve the output of the stanford alpaca dataset☆12Updated last year
- Multi-Domain Expert Learning☆67Updated 7 months ago
- ☆42Updated last year
- ☆18Updated this week
- C++ inference wrappers for running blazing fast embedding services on your favourite serverless like AWS Lambda. By Prithivi Da, PRs welc…☆21Updated 6 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated 5 months ago