Pinned Repositories
bayesopt
BayesOpt: A toolbox for bayesian optimization, experimental design and stochastic bandits.
Chinese-RC-Dataset
A Chinese Cloze-style RC Dataset: People Daily & Children's Fairy Tale (CFT)
crx2xpi-ffext
Convert Chrome Web Extensions to Firefox
MetaGPT
🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
MOSS-RLHF
MOSS-RLHF
pytorch_structure2vec
pytorch implementation of structure2vec (https://arxiv.org/abs/1603.05629)
spinn
SPINN (Stack-augmented Parser-Interpreter Neural Network): fast, batchable, context-aware TreeRNNs
VikingMew's Repositories
VikingMew/MetaGPT
🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
VikingMew/MOSS-RLHF
MOSS-RLHF
VikingMew/Bert-VITS2
vits2 backbone with bert
VikingMew/ChatGLM-6B
ChatGLM-6B:开源双语对话语言模型
VikingMew/ChatGPT
Reverse engineered ChatGPT API. Uses official model same as the website.
VikingMew/DeepSpeedExamples
Example models using DeepSpeed
VikingMew/DiffSinger
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Forked and maintained by the OpenVPI community
VikingMew/dolly
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
VikingMew/emotional-vits
无需情感标注的情感可控语音合成模型,基于VITS
VikingMew/generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
VikingMew/LLM-RGB
LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.
VikingMew/LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
VikingMew/MidJourney-Wrapper
MidJourney wrapper in Discord.
VikingMew/minimal-sd
VikingMew/MoeSS
使用C++ OnnxRuntime 重构了Tacotron2、VITS、SoVIts、DiffSvc和DiffSinger推理的集成UI软件
VikingMew/MOSS
An open-source tool-augmented conversational language model from Fudan University
VikingMew/open_flamingo
An open-source framework for training large multimodal models
VikingMew/OpenChineseLLaMA
Inference code for LLaMA models
VikingMew/Prompt-hunter
Save the Prompt and images from the Midjourney details page to your Notion page
VikingMew/Retrieval-based-Voice-Conversion-WebUI
Voice data <= 10 mins can also be used to train a good VC model!
VikingMew/silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector, Language Classifier and Spoken Number Detector
VikingMew/skyagi
SkyAGI: Emerging human-behavior simulation capability in LLM
VikingMew/so-vits-svc
SoftVC VITS Singing Voice Conversion
VikingMew/so-vits-svc-4.0-v2
SoftVC VITS Singing Voice Conversion
VikingMew/stable-diffusion-webui
Stable Diffusion web UI
VikingMew/stablediffusion
High-Resolution Image Synthesis with Latent Diffusion Models
VikingMew/vits-raw
VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai
VikingMew/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
VikingMew/youtube-dl
Command-line program to download videos from YouTube.com and other video sites
VikingMew/z-bench
Z-Bench 1.0 by 真格基金:一个麻瓜的大语言模型中文测试集。Z-Bench is a LLM prompt dataset for non-technical users, developed by an enthusiastic AI-focused team in Zhenfund.