JuLian1130

BAdam

ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, Axolotl, etc.

Mr.-Ranedeer-AI-Tutor

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

dbrx

Code examples and resources for DBRX, a large language model developed by Databricks

gpt4free

The official gpt4free repository | various collection of powerful language models

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.

sherpa-ncnn

Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, VisionFive2, LicheePi4A etc.

nm-vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

mozc-devices

Automatically exported from code.google.com/p/mozc-morse

banfoStyle

半佛风格视频生成器

StableCascade

Official Code for Stable Cascade

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

ZLUDA

CUDA on AMD GPUs

visualwebarena

VisualWebArena is a benchmark for multimodal agents.

vim-dict

没办法，被逼的，重新整理一个词典补全的数据库

Best-Flutter-UI-Templates

completely free for everyone. Its build-in Flutter Dart.

langgraph

Build resilient language agents as graphs.

MobileAgent

Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

MiniCPM

MiniCPM-2B: An end-side LLM outperforms Llama2-13B.

LLMFarm

llama and other large language models on iOS and MacOS offline using GGML library.

tts-server-android

这是一个Android系统TTS应用，内置微软演示接口，可自定义HTTP请求，可导入其他本地TTS引擎，以及根据中文双引号的简单旁白/对话识别朗读 ，还有自动重试，备用配置，文本替换等更多功能。

legado

Legado 3.0 Book Reader with powerful controls & full functions❤️阅读3.0, 阅读是一款可以自定义来源阅读网络内容的工具，为广大网络文学爱好者提供一种方便、快捷舒适的试读体验。

OpenAOE

LLM Group Chat Framework: chat with multiple LLMs at the same time. 大模型群聊框架：同时与多个大语言模型聊天。

chain-of-thought-hub

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

AlphaCodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

FuseAI

FuseLLM & FuseChat Project