877623423

mergekit

Tools for merging pretrained large language models.

mamba

Mamba SSM architecture

alignment-handbook

Robust recipes to align language models with human and AI preferences

trl

Train transformer language models with reinforcement learning.

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

megablocks

langchain

🦜🔗 Build context-aware reasoning applications

ChatGPT-Next-Web

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

fanqie-novel-download

番茄小说下载的Python实现。

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Aquila2

The official repo of Aquila2 series proposed by BAAI, including pretrained & chat large language models.

Bert-VITS2

vits2 backbone with bert

whisper-vits-svc

Core Engine of Singing Voice Conversion & Singing Voice Clone

fairseq2

FAIR Sequence Modeling Toolkit 2

Genshin_Datasets

Genshin Datasets For SVC/SVS/TTS

Bert-VITS2

vits2 backbone with multilingual-bert

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

h2o-llmstudio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/

Firefly

Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

MindChat

🐋MindChat（漫谈）——心理大模型：漫谈人生路, 笑对风霜途

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Whisper-Finetune

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment

IF

generative-models

Generative Models by Stability AI

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

AnimateDiff

Official implementation of AnimateDiff.