fine-tuning

This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

Fine-tuning an LLM using a Generic Workflow and Best Practices with PyTorch

No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models (ICLR 2022)

BERT Fine-tuning for Aspect Based Sentiment Analysis

This repository uses pretrain BERT embeddings for transfer learning in QA domain

MediBeng Whisper Tiny improves doctor-patient transcription by training the Whisper Tiny model to translate mixed Bengali-English speech into English, making it easier for analysis, record-keeping, and using AI in healthcare.

用于微调LLM的中文指令数据集

Reproduction of CGCNN for predicting material properties

Train transformer-based models.

A fluent, scalable, and easy-to-use LLM data processing framework.

Web Scraping, Document Deduplication & GPT-2 Fine-tuning with a newly created scam dataset.

A set of jupyter notebooks

🎈 Structure-aware adapter fine-tuning PLMs, with high training speed and impressive performance (Journal of Chemical Information and Modeling 2024).

Implementation of Bitune: Bidirectional Instruction-Tuning

[ISSTA 2024] PatchFinder: A Two-Phase Approach to Security Patch Tracing for Disclosed Vulnerabilities in Open Source Software

A minimal tool to generate and validate datasets.

A simple, interactive CLI for fine-tuning small language models on Apple Silicon. No YAML configs, no complex flags - just an interactive CLI that guides you through the process.

Turn documents into high-quality instruction datasets with grounding, quality filtering, deduplication, and provenance.

AnnoTheia is a data annotation toolkit that identifies when a person speaks in a scene and transcribes their speech, also offering flexibility to replace modules for different languages.