rogeriofreitasghb's repositories
RWKV-World-Finetune
Fine-tuning RWKV-World model
ai00_rwkv_server
A localized open-source AI server that is better than ChatGPT.
BetterChatGPT
An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)
eplm
Evaluation of Portuguese Language Models
Free-Auto-GPT
Free Auto GPT with NO paids API is a repository that offers a simple version of Auto GPT, an autonomous AI agent capable of performing tasks independently. Unlike other versions, our implementation does not rely on any paid OpenAI API, making it accessible to anyone.
Gepeto
A simple project with Fabrice Bellard's ts_server backend and ChatGPT-generated frontend
gorilla
Gorilla: An API store for LLMs
langflow
⛓️ LangFlow is a UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows.
lora-instruct
Instruct-tune LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA
matrix-docker-ansible-deploy
🐳 Matrix (An open network for secure, decentralized communication) server setup using Ansible and Docker
ufsc_repositorio
This is a dataset repo for translations pairs most Portuguese English from the UFSC repository.
LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
MIDI-LLM-tokenizer
Tools for converting .mid files into text for training large language models
NBCE
Naive Bayes-based Context Extension
nofwl_bellard
NoFWL Desktop Application for bellard Text Synt Server
RasaGPT
💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram
rwkv-cpp-cuda
A torchless, c++ rwkv implementation using 8bit quantization, written in cuda
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.
rwkv-midi-stream
Uses FluidSynth to play an infinite stream of AI generated MIDI in real time
RWKV_chains
Enhancing LangChain prompts to work better with RWKV models
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
smol-dev-js
Smol personal AI, for smol incremental tasks in a JS project
Tuga
Turtl Server Fork For Study.
web-rwkv
Implementation of the RWKV language model in pure WebGPU/Rust.