An innovative library for efficient LLM inference via low-bit quantization

Collection of resources for finetuning Large Language Models (LLMs).

Chaining thoughts and LLMs to learn DNA structural biophysics

FlowerTune LLM on Medical Dataset

Schematic Blueprint for Finetuning LLM (e.g. Qwen or Llama) for text classification using LORA. Output model can have original or modified head (e.g. for SequenceClassification).

Django implementation of CodeBERT for detecting vulnerable code.

FlowerTune LLM on Medical Dataset

This repository contains all the notebooks, resources, and documentation used to develop and evaluate models for the Automated Essay Scoring (AES) Kaggle competition. The project aims to build an open-source solution for automated essay evaluation to support educators and provide timely feedback to students.

A web app for detecting plagiarism between two PDFs. Users can upload PDF files, and the app will detect plagiarism by leveraging a fine-tuned LLM model (SmolLM2-135M) trained on the MIT Plagiarism Detection Dataset.

FlowerTune LLM on NLP Dataset

Implemented and fine-tuned BERT for a custom sequence classification task, leveraging LoRA adapters for efficient parameter updates and 4-bit quantization to optimize performance and resource utilization.

ARC-Test-Time-Training (ARC-TTT)

Llama 3 fine-tuning to generate SQL statements from Text inputs.

Fine-tune large language models (LLMs) using the Hugging Face Transformers library.

FlowerTune LLM on NLP Dataset