A series of math-specific large language models of our Qwen2 series.

A framework for few-shot evaluation of language models.

To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 🍓

Official repository for "NoLiMa: Long-Context Evaluation Beyond Literal Matching"

[Nat. Comm. 2024] Multimodal learning for chemical domain, with SMILES and properties.

Code for EMNLP2023 paper "MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter".

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

A series of technical report on Slow Thinking with LLM

LOFT: A 1 Million+ Token Long-Context Benchmark

ACL 2024 | LooGLE: Long Context Evaluation for Long-Context Language Models

A collection of AWESOME things about Graph-Related LLMs.

open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality

A Survey on Large Language Model-Based Game Agents

A small counter that counts how many changes you have made since this extension been installed.

A universal time series representation learning framework

clash for windows汉化版. 提供clash for windows的汉化版, 汉化补丁及汉化版安装程序

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

🪺 A simple, clean, flexible Hugo theme