yangjianxin1/LongQLoRA
LongQLoRA: Extent Context Length of LLMs Efficiently
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.
Stars
168
Forks
16
Language
Python
License
—
Category
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.
Higher-rated alternatives
OptimalScale/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
adithya-s-k/AI-Engineering.academy
Mastering Applied AI, One Concept at a Time
jax-ml/jax-llm-examples
Minimal yet performant LLM examples in pure JAX
young-geng/scalax
A simple library for scaling up JAX programs
riyanshibohra/TuneKit
Upload your data → Get a fine-tuned SLM. Free.