di37/full-fine-tuning-nvidia-question-and-answering
Flan-t5-base model was fine-tuned on Nvidia Question and Answer Pair Dataset available on Kaggle. This is a beginner level project who wants to step in to the world of Large Language Models.
This project offers a foundational guide for developers new to Large Language Models (LLMs). It walks you through fine-tuning a pre-existing model for question-answering, taking in NVIDIA-specific question-answer pairs and producing a specialized model capable of answering questions about NVIDIA topics. This is ideal for early-career machine learning engineers or data scientists looking to build practical LLM skills.
No commits in the last 6 months.
Use this if you are a developer seeking hands-on experience in the practical steps of fine-tuning an LLM for a specific question-answering task.
Not ideal if you are looking for a pre-trained, production-ready model or a deep dive into advanced LLM architectures and optimization techniques.
Stars
22
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Apr 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/di37/full-fine-tuning-nvidia-question-and-answering"
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.