This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive A…

Must-read Papers on LLM Agents.

awesome papers in LLM interpretability

A PyTorch-based Speech Toolkit

Training Sparse Autoencoders on Language Models

A unified interface for computing surprisal (log probabilities) from language models! Supports neural, symbolic, and black-box API models.

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

AI Inferencing at the Edge. A simple one-file way to run various GGML models with KoboldAI's UI with AMD ROCm offloading

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Official implementations for (1) BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation and (2) Discourse Centric Evaluation of Machine Translation with a Densely Annotated P…

Awesome papers involving LLMs in Social Science.

BEANS: The Benchmark of Animal Sounds

Instant voice cloning by MIT and MyShell.

Mindcraft, the open-source NLP solution to craft the minds of your NPC characters for your videogames.

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

An evaluation bentchmark for classical Chinese

Unsupervised text tokenizer for Neural Network-based text generation.

A playbook for systematically maximizing the performance of deep learning models.

A neural language model that estimates incremental processing complexity

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

String-to-String Algorithms for Natural Language Processing

对常用的6700个汉字进行音、形比较，输出音近字、形近字的列表。 # 相近字

🦜🔗 Build context-aware reasoning applications

Keep track of big models in audio domain, including speech, singing, music etc.