merantix-momentum/acip
🗜️Codebase of the ACIP algorithm 🗜️
This project helps machine learning practitioners and researchers reduce the size of large language models (LLMs). It takes an existing LLM, such as LLaMA or Mistral, and outputs a significantly smaller, compressed version that still performs well. Users can easily choose their desired compression level, making models more efficient for deployment and experimentation.
Use this if you need to make large language models smaller and faster, or reduce their memory footprint, while maintaining good performance.
Not ideal if you are looking for a pre-trained LLM for immediate use without any compression needs, or if you require an extremely tiny model where advanced knowledge distillation might be more suitable.
Stars
16
Forks
1
Language
Python
License
—
Category
Last pushed
Feb 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/merantix-momentum/acip"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aalok-sathe/surprisal
A unified interface for computing surprisal (log probabilities) from language models! Supports...
EvolvingLMMs-Lab/lmms-engine
A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
FunnySaltyFish/Better-Ruozhiba
【逐条处理完成】人为审核+修改每一条的弱智吧精选问题QA数据集
reasoning-machines/pal
PaL: Program-Aided Language Models (ICML 2023)
microsoft/monitors4codegen
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static...