JIA-Lab-research/LongLoRA

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

46
/ 100
Emerging

This project provides large language models (LLMs) that can understand and generate text based on very long documents, like entire reports or books. It takes long text inputs and produces summaries, answers, or creative content. Anyone who needs to process extensive textual information, such as researchers, analysts, or content creators, would find this useful.

2,694 stars. No commits in the last 6 months.

Use this if you need to work with Large Language Models that can handle extremely long documents or conversations, retaining context over thousands of words.

Not ideal if you only work with short prompts or single-turn questions, as its main advantage is processing extended context.

long-document-analysis extended-context-processing text-summarization information-extraction conversational-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

2,694

Forks

292

Language

Python

License

Apache-2.0

Category

llm-fine-tuning

Last pushed

Aug 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/JIA-Lab-research/LongLoRA"

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