ssbuild / rwkv_finetuning
rwkv finetuning
☆36Updated 11 months ago
Alternatives and similar repositories for rwkv_finetuning:
Users that are interested in rwkv_finetuning are comparing it to the libraries listed below
- 实现Blip2RWKV+QFormer的多模态图文 对话大模型,使用Two-Step Cognitive Psychology Prompt方法,仅3B参数的模型便能够出现类人因果思维链。对标MiniGPT-4,ImageBind等图文对话大语言模型,力求以更小的算力和资源实…☆38Updated last year
- ☆110Updated last week
- This project is established for real-time training of the RWKV model.☆49Updated 10 months ago
- ☆82Updated 10 months ago
- ☆13Updated 3 months ago
- ☆43Updated last year
- ✅4g GPU可用 | 简易实现ChatGLM单机调用多个计算设备(GPU、CPU)进行推理☆34Updated last year
- SUS-Chat: Instruction tuning done right☆48Updated last year
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆35Updated last week
- 用户友好、开箱即用的 RWKV Prompts 示例,适用于所有用户。Awesome RWKV Prompts for general users, more user-friendly, ready-to-use prompt examples.☆34Updated last month
- VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.☆212Updated 2 weeks ago
- Fine-tuning RWKV-World model☆25Updated last year
- share data, prompt data , pretraining data☆35Updated last year
- RAG SYSTEM FOR RWKV☆45Updated 3 months ago
- 一个基于Flask实现的RWKV_Role_Playing项目的API。☆30Updated 8 months ago
- 基于RWKV模型的角色扮演,实际上是个改的妈都不认识的 RWKV_Role_Playing☆16Updated last year
- This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation…☆125Updated 8 months ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated 7 months ago
- Its an open source LLM based on MOE Structure.☆58Updated 8 months ago
- A simple way to synthesize LLM training data. (under construction⚠)☆16Updated last month
- This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the …☆47Updated 3 months ago
- The paddle implementation of meta's LLaMA.☆45Updated last year
- GLM Series Edge Models☆132Updated last month
- qwen models finetuning☆93Updated 2 weeks ago
- Just for debug☆56Updated last year
- ☆21Updated last year
- Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory☆28Updated 10 months ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆56Updated 11 months ago
- deep learning☆150Updated 2 weeks ago