Pinned Repositories
llama-moe
⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)
awesome-lm-evaluation
🩺 A collection of ChatGPT evaluation reports on various bechmarks.
CatalogExtraction
🌳CED: Catalog Extraction from Documents
DocEE
🕹️ A toolkit for document-level event extraction, containing some SOTA model implementations.
Humback
🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.
Mirror
🪞A powerful toolkit for almost all the Information Extraction tasks.
MoE-SFT
🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts
paper-hero
💪 A toolkit to help search for papers from aclanthology, arXiv and dblp.
random-luck
Automatically select the best random seed based on ancient Chinese I Ching. Good luck and best wishes !
watchmen
😎 A simple and easy-to-use toolkit for GPU scheduling.
Spico197's Repositories
Spico197/DocEE
🕹️ A toolkit for document-level event extraction, containing some SOTA model implementations.
Spico197/Humback
🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.
Spico197/Mirror
🪞A powerful toolkit for almost all the Information Extraction tasks.
Spico197/MoE-SFT
🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts
Spico197/REx
🎮 A toolkit for Relation Extraction and more...
Spico197/CatalogExtraction
🌳CED: Catalog Extraction from Documents
Spico197/accept
Will my paper be accepted?
Spico197/feishu-alert-bots
Spico197/smoe-eval
For smoe models evaluation. Commit: b281b0921b636bc36ad05c0b0b0763bd6dd43463
Spico197/Spico197.github.io
ZHU Tong's homepage.
Spico197/TaskLAMA
🚩 An unoffical implementation of TaskLAMA.
Spico197/TaskPlanningPapers
🥅 A collection of task planning papers.
Spico197/daily-arxiv
Daily arXiv feed
Spico197/awesome-idol-papers
Spico197/Awesome-Mixture-of-Experts-Papers
A curated reading list of research in Mixture-of-Experts(MoE).
Spico197/azure-openai
API testcase.
Spico197/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Spico197/graduate
Spico197/llama-moe
⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
Spico197/LLM-Terminologies
A collection of terminologies about LLM.
Spico197/mergekit
Tools for merging pretrained large language models.
Spico197/MyArxiv
Daily arXiv feed
Spico197/nanoT5
Fast & Simple repository for pre-training and fine-tuning T5-style models
Spico197/nanotron
Minimalistic large language model 3D-parallelism training
Spico197/OpenBA
OpenBA: An Open-Sourced 15B Bilingual Asymmetric Seq2Seq Model Pre-trained from Scratch
Spico197/opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.
Spico197/python-template
🗞️ A template for creating new Python projects.
Spico197/Spico197
Spico197/transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
Spico197/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs