Sparsify transformers with SAEs and transcoders

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek3, ...) and 150+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, Inter…

Tools for merging pretrained large language models.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Reference implementation for DPO (Direct Preference Optimization)

Strong and Open Vision Language Assistant for Mobile Devices

The official GitHub page for the survey paper "A Survey of Large Language Models".

国家自然科学基金申请书正文（面上项目）LaTeX 模板（非官方）

LLM Finetuning with peft

jiant is an nlp toolkit

Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101

Code and data associated with the AmbiEnt dataset in "We're Afraid Language Models Aren't Modeling Ambiguity" (Liu et al., 2023)

UESTC Thesis Latex Template 2023. It fully supports the latest format specification in 2023, supports independent symbol table, abbreviation table, and complete and fully customizable Academic/Prof…

Interpretable Evaluation for AI Systems

Data and information related to the Books3 dataset included as part of The Pile, and used to train Meta's LLaMA among others

Slides for the ChatGPT Masterclass

Code and model card templates accompanying the paper "Towards Climate Awareness in NLP Research"

A reading list of up-to-date papers on NLP for Social Good.