Stars
Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
Train transformer language models with reinforcement learning.
lishiying410 / ML-NLP
Forked from NLP-LOVE/ML-NLP此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Fast and memory-efficient exact attention
A high-throughput and memory-efficient inference and serving engine for LLMs
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The official repository for the The Project Dialogism Novel Corpus, a dataset of annotated quotations in full-length English novels.
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)
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。
Example projects built with the Hume AI APIs
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.
A Comprehensive Benchmark to Evaluate LLMs 8046 as Agents (ICLR'24)
AgentTuning: Enabling Generalized Agent Abilities for LLMs
Making large AI models cheaper, faster and more accessible
OneDiff: An out-of-the-box acceleration library for diffusion models.
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡
斯坦福工作 Generative Agents的复现和翻译 An attempt to build a working, locally-running cheap version of Generative Agents: Interactive Simulacra of Human Behavior
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型