NanQiAi's repositories
mem0
The memory layer for Personalized AI
Retrieval-based-Voice-Conversion-WebUI
Easily train a good VC model with voice data <= 10 mins!
ChatTTS
ChatTTS is a generative speech model for daily dialogue.
litellm
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
flagsmith
Open Source Feature Flagging and Remote Config Service. Host on-prem or use our hosted version at https://flagsmith.com/
caesium-image-compressor
Caesium is an image compression software that helps you store, send and share digital pictures, supporting JPG, PNG and WebP formats. You can quickly reduce the file size (and resolution, if you want) by preserving the overall quality of the image.
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
LLaVA
Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
pykan
Kolmogorov Arnold Networks
Yi
A series of large language models trained from scratch by developers @01-ai
LLaMA-Efficient-Tuning
Fine-tuning LLaMA with PEFT (PT+SFT+RLHF with QLoRA)
ollama
Get up and running with Llama 3, Mistral, Gemma, and other large language models.
cat-catch
猫抓 chrome资源嗅探扩展
ollama-python
Ollama Python library
great-tables
Easily generate information-rich, publication-quality tables from Python
outline
The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.
dify
One API for plugins and datasets, one interface for prompt engineering and visual operation, all for creating powerful AI applications.
CompreFace
Leading free and open-source face recognition system
python-miio
Python library & console tool for controlling Xiaomi smart appliances
LLMBook-zh.github.io
《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣
WizardLM
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
OmniLMM
Large Multi-modal Models for Strong Performance and Efficient Deployment
MiniCPM
MiniCPM-2.4B: An end-side LLM outperforms Llama2-13B.
fdroidclient
Android client application.
cppinsights
C++ Insights - See your source code with the eyes of a compiler
llm.c
LLM training in simple, raw C/CUDA
AIOS
AIOS: LLM Agent Operating System
Chinese-Vicuna
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca