Highlights
- Pro
Stars
Enhance the ChatGLM with the MoE prefix embedding
SecGPT: An execution isolation architecture for LLM-based systems
Survey of NLP+AI Conferences and Journals for NLPers
CMMLU: Measuring massive multitask language understanding in Chinese
We aim to provide the best references to search, select, and synthesize high-quality and large-quantity data for post-training your LLMs.
A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。
All available datasets for Instruction Tuning of Large Language Models
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
[ICML 2024] Official repository for "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"
A series of math-specific large language models of our Qwen2 series.
Curated list of datasets and tools for post-training.
LLM Finetuning with peft
A library for advanced large language model reasoning
An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git
📄 适合中文的简历模板收集（LaTeX，HTML/JS and so on）由 @hoochanlon 维护
CVPR and NeurIPS poster examples and templates. May we have in-person poster session soon!
Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
Data and tools for generating and inspecting OLMo pre-training data.
Code for the paper 🌳 Tree Search for Language Model Agents
Train transformer language models with reinforcement learning.
[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
A framework for few-shot evaluation of language models.
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
DSPy: The framework for programming—not prompting—language models