Stars
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
The most modern LLM evaluation toolkit
vision-language study material
Official implementation of project Honeybee (CVPR 2024)
Get your documents ready for gen AI
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
S2APLER: S2 Agglomeration of Papers with Low Error Rate (it's for academic paper clustering)
한국어 언어 모델 학습을 위한 프로젝트(Flax, Pytorch with Huggingface Accelerate)
[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
Industry leading face manipulation platform
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Open-WikiTable :Dataset for Open Domain Question Answering with Complex Reasoning over Table
FacTool: Factuality Detection in Generative AI
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files
Generative Models by Stability AI
Large Language Model Text Generation Inference
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
KoLLaVA: Korean Large Language-and-Vision Assistant (feat.LLaVA)
evolve llm training instruction, from english instruction to any language.
Hackable and optimized Transformers building blocks, supporting a composable construction.