newbietuan
Follow
Stars
The hub for EleutherAI's work on interpretability and learning dynamics
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
Chat with any PDF. Easily upload the PDF documents you'd like to chat with. Instant answers. Ask questions, extract information, and summarize documents with AI. Sources included.
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW
Fast and memory-efficient exact attention
llama3 implementation one matrix multiplication at a time
Building a quick conversation-based search demo with Lepton AI.
text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。
A work in progress. Trying to write about all interesting or necessary pieces in the current development of LLMs and generative AI. Gradually adding more topics.
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
Foundational Models for State-of-the-Art Speech and Text Translation
Source code for NAACL 2022 paper Weakly Supervised Text Classification using Supervision Signals from a Language Mode
The code for the ACL 2023 paper "Linear Classifier: An Often-Forgotten Baseline for Text Classification".
A library for multi-class and multi-label classification
Official resources of "Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification" (ACL 2023 long).
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)