Stars
Fara-7B: An Efficient Agentic Model for Computer Use
[ACL 2024] ChartAssistant is a chart-based vision-language model for universal chart comprehension and reasoning.
✨ [ACL 2025] Incorporating Domain Knowledge into Materials Tokenization
A high-throughput and memory-efficient inference and serving engine for LLMs
AgentTuning: Enabling Generalized Agent Abilities for LLMs
🤗 smolagents: a barebones library for agents that think in code.
Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools"
Official repository for Mi:dm 2.0, the large language model developed by KT.
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filli…
MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science (EMNLP 2024(Findings))
Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning (ACL 2024)
Official repository for "Mentor-KD: Making Small Language Models Better Multi-step Reasoners", EMNLP 2024
Source code of DRAGIN, ACL 2024 main conference Long Paper (Oral)
The repository contains the code for our EMNLP 2023 paper "SMoP: Towards Efficient and Effective Prompt Tuning with Sparse Mixture-of-Prompts", written by Joon-Young Choi, Junho Kim, Jun-Hyung Park…
An experimental implementation of the retrieval-enhanced language model
Toolkit for downloading and processing Google's AudioSet dataset.
Pytorch implementations of Client-Customized Adaptation for Parameter-Efficient Federated Learning (Findings of ACL: ACL 2023)
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
Large Language Models Are Reasoning Teachers (ACL 2023)
Instruct-tune LLaMA on consumer hardware
Forward-Looking Active REtrieval-augmented generation (FLARE)
OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
Pytorch implementations of Co-teaching for noisy label learning