harrisonvanderbyl / rwkv_chatbot
rwkv_chatbot
β62Updated 2 years ago
Alternatives and similar repositories for rwkv_chatbot:
Users that are interested in rwkv_chatbot are comparing it to the libraries listed below
- ChatGPT-like Web UI for RWKVsticβ100Updated last year
- π β Notebooks related to RWKVβ59Updated last year
- Framework agnostic python runtime for RWKV modelsβ146Updated last year
- BlinkDL's RWKV-v4 running in the browserβ47Updated 2 years ago
- An unsupervised model merging algorithm for Transformers-based language models.β104Updated 11 months ago
- Image Diffusion block merging technique applied to transformers based Language Models.β54Updated last year
- β27Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRAβ123Updated last year
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge promptsβ112Updated last year
- This project aims to make RWKV Accessible to everyone using a Hugging Face like interface, while keeping it close to the R and D RWKV braβ¦β64Updated last year
- C/C++ implementation of PygmalionAI/pygmalion-6bβ56Updated last year
- Instruct-tuning LLaMA on consumer hardwareβ66Updated 2 years ago
- Model REVOLVER, a human in the loop model mixing system.β33Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMsβ77Updated 11 months ago
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.β71Updated 2 years ago
- Conversational Language model toolkit for training against human preferences.β42Updated 11 months ago
- Just a simple HowTo for https://github.com/johnsmith0031/alpaca_lora_4bitβ31Updated last year
- 4 bits quantization of LLMs using GPTQβ48Updated last year
- Our data munging code.β34Updated 6 months ago
- Instruct-tune LLaMA on consumer hardwareβ73Updated last year
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenciβ¦β310Updated last year
- Where we keep our notes about model training runs.β16Updated 2 years ago
- RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.β67Updated 2 years ago
- Text WebUI extension to add clever Notebooks to Chat modeβ139Updated last year
- β42Updated 2 years ago
- GPT-2 small trained on phi-like dataβ65Updated last year
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best β¦β414Updated last year
- tinygrad port of the RWKV large language model.β44Updated 3 weeks ago
- A finetuning pipeline for instruct tuning Raven 14bn using QLORA 4bit and the Ditty finetuning libraryβ28Updated 9 months ago
- Full finetuning of large language models without large memory requirementsβ93Updated last year