IAAR-Shanghai/FastMem
Fast Memorization of Prompt Improves Context Awareness of Large Language Models (Findings of EMNLP 2024)
This tool helps researchers and AI practitioners improve how Large Language Models (LLMs) understand and use contextual information. By efficiently fine-tuning a small part of the LLM, it helps the model "memorize" prompt details without overfitting. The result is an LLM that is better at responding accurately based on the given context in tasks like Q&A and summarization.
No commits in the last 6 months.
Use this if you are working with Large Language Models and need to significantly boost their ability to comprehend and accurately follow context from prompts in tasks like question answering or summarization.
Not ideal if you are looking for a general-purpose LLM fine-tuning solution that modifies the entire model, rather than focusing on context awareness through targeted prompt memorization.
Stars
24
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IAAR-Shanghai/FastMem"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jncraton/languagemodels
Explore large language models in 512MB of RAM
microsoft/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
haizelabs/verdict
Inference-time scaling for LLMs-as-a-judge.
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models
bytedance/Sa2VA
Official Repo For Pixel-LLM Codebase