PyTorch extensions for high performance and large scale training.

The official Meta Llama 3 GitHub site

Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

Source code of ACL 2023 accepted paper "AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression"

EMNLP'2023: Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration

Python package for string algorithms ➰

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…

Prod Env

Code and documentation to train Stanford's Alpaca models, and generate the data.

LOG-Means算法是一种新型、简化的、高效、对大数据集和大搜索空间具有强鲁棒性的簇数目估计方法。它采用了二分搜索策略和递归细化策略，分别在大范围和小范围内进行簇数目估计，从而高效估计数据中的簇的个数。

Unsupervised text tokenizer for Neural Network-based text generation.

Inference code for Llama models

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

TensorFlow code and pre-trained models for BERT