likelyzhao

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

AI-Vtuber

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊天。它使用TTS技术【edge-tts/VITS/elevenlabs/bark/bert-vits2/睿声】生成回答并可以选择【so-vits-svc/DDSP-SVC】变声；指令协同SD画图。

llama.cpp

LLM inference in C/C++

InternLM

Official release of InternLM2.5 base and chat models. 1M context support

wild-gaussians

WildGaussians: 3D Gaussian Splatting In the Wild

cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Marigold

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

LLM-Agent-Survey

Megatron-LLM

distributed trainer for LLMs

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

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

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Megatron-LM

Ongoing research training transformer models at scale

gradio-pdf

Source code of the gradio_pdf custom component.

TextBox

TextBox 2.0 is a text generation library with pre-trained language models

CDial-GPT

A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

coco-cn

Enriching MS-COCO with Chinese sentences and tags for cross-lingual multimedia tasks

awesome-grounding

awesome grounding: A curated list of research papers in visual grounding

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

VideoGPT

Document-Layout-Analysis

Object Detection Model for Scanned Documents

Chinese_reading_task_eeg_processing

Chinese-LangChain

中文langchain项目|小必应，Q.Talk，强聊，QiangTalk

Baichuan-7B

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Python_About_Finance

VisualGLM-6B

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型