kobako's starred repositories
Awesome-LLM-Strawberry
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
bert-extractive-summarizer
Easy to use extractive text summarization with BERT
starling-agent
STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models
lightnovel-2023
:books: 轻小说2023
bilibili-API-collect
哔哩哔哩-API收集整理【不断更新中....】
simple_tfidf_japanese
日本語専用のTFIDF計算機。日本語文章を類似度で比較できる。
GeneralPolicySpeechOfPrimeMinisterOfJapan
This is the corpus of Japanese Text that general policy speech of prime minister of Japan
commonsense-rl
Knowledge-Aware RL agents with Commonsense Reasoning
agent-protocol
Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.
blindfold-textgame
[NAACL 2021] Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents
pytorch-crf
(Linear-chain) Conditional random field in PyTorch.
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
MilkyTracker
An FT2 compatible music tracker
japanize-matplotlib
install & import するだけで matplotlib を日本語表示対応させる
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
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-Runner
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.
RWKV-LM
RWKV is an 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.