WhereIsAI/BiLLM
Tool for converting LLMs from uni-directional to bi-directional by removing causal mask for tasks like classification and sentence embeddings. Compatible with ๐ค transformers.
This tool helps AI/ML engineers modify large language models (LLMs) to improve their performance on specific tasks like text classification and generating sentence embeddings. It takes existing uni-directional LLMs (like LLaMA or Mistral) and converts them to a bi-directional format, producing more accurate models for certain applications. This is designed for AI/ML engineers working on fine-tuning LLMs for downstream tasks.
No commits in the last 6 months.
Use this if you are an AI/ML engineer who needs to enhance the performance of specific large language models for tasks like text classification, named entity recognition, or creating sentence embeddings.
Not ideal if you are an end-user looking for a ready-to-use application, or if you are not comfortable working with model fine-tuning and the Hugging Face `transformers` library.
Stars
65
Forks
9
Language
Python
License
MIT
Category
Last pushed
Dec 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WhereIsAI/BiLLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
meta-llama/llama-cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started...
arcee-ai/mergekit
Tools for merging pretrained large language models.
changyeyu/LLM-RL-Visualized
๐100+ ๅๅ LLM / RL ๅ็ๅพ๐๏ผใๅคงๆจกๅ็ฎๆณใไฝ่ ๅทจ็ฎ๏ผ๐ฅ๏ผ100+ LLM/RL Algorithm Maps ๏ผ
mindspore-lab/step_into_llm
MindSpore online courses: Step into LLM