A fine-tuned LLM great at answering questions about car repairs and maintenance.

Stumble upon a fine tuning that is unfathomable.

Dialogue Summary LLM - FLAN - T5: An implementation of the Flan-t5 LLM to summarize dialogues. Prompt Engineering , Fine tuning with PEFT and fine tuning with RL (PPO) is explored within this project.

This project is an implementation of the paper: Parameter-Efficient Transfer Learning for NLP, Houlsby [Google], ICML 2019.

This repo contains implementations of fine-tuning LLaMA LLM model using LoRA weights (PEFT) as well as focuses on the Retrieval Augmented Generation (RAG) framework.

This repository was commited under the action of executing important tasks on which modern Generative AI concepts are laid on. In particular, we focussed on three coding actions of Large Language Models. Extra and necessary details are given in the README.md file.

Fine-tune StarCoder2-3b for SQL tasks on limited resources with LORA. LORA reduces model size for faster training on smaller datasets. StarCoder2 is a family of code generation models (3B, 7B, and 15B), trained on 600+ programming languages from The Stack v2 and some natural language text such as Wikipedia, Arxiv, and GitHub issues.

Using Open-Source LLMs like FLAN-T5, built a Dialog Summarization model and did fine-tuning with DialogSum HF Dataset

CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language Model

Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"

This repo contains everything about transformers and NLP.

memory-efficient fine-tuning; support 24G GPU memory fine-tuning 7B

Mistral and Mixtral (MoE) from scratch

Fine-tuning Llama3 8b to generate JSON formats for arithmetic questions and process the output to perform calculations.

Fine Tuning pegasus and flan-t5 pre-trained language model on dialogsum datasets for conversation summarization to to optimize context window in RAG-LLMs

A bash scripting assistant that helps you automate tasks. Powered by a streamlit chat interface, A finetuned nl2bash model generates bash code from natural language descriptions provided by the user

[ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference

PEFT is a wonderful tool that enables training a very large model in a low resource environment. Quantization and PEFT will enable widespread adoption of LLM.

For this project, I fine-tuned two separate models for three tasks: document summarization, dialogue summarization and text classification