yangjianxin1/LongQLoRA

LongQLoRA: Extent Context Length of LLMs Efficiently

31
/ 100
Emerging

This project helps machine learning engineers and researchers efficiently extend the context window of large language models (LLMs). It takes existing LLMs, like LLaMA2 7B/13B or Vicuna 13B, and significantly increases the amount of text they can process at once—from 4096 tokens to 8192 or even 12k tokens. The output is a finetuned LLM capable of understanding and generating longer texts.

168 stars. No commits in the last 6 months.

Use this if you need to work with very long documents for tasks like summarization, question answering over extensive texts, or processing large codebases, and want to achieve this with less demanding GPU resources than other methods.

Not ideal if your primary goal is to train a new LLM from scratch or if your tasks only involve short, conversational interactions that don't require extended context understanding.

large-language-models natural-language-processing machine-learning-engineering text-generation long-document-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

168

Forks

16

Language

Python

License

Category

llm-fine-tuning

Last pushed

Nov 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/yangjianxin1/LongQLoRA"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.