Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Machine Learning Engineering Open Book

Ongoing research training transformer models at scale

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

A PyTorch-based Speech Toolkit

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

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

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

BertViz: Visualize Attention in Transformer Models

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.