GPT is a family of AI models built by OpenAI. It stands for Generative Pre-trained Transformer, which is basically a description of what the AI models do and how they work (I’ll dig into that more in a minute).
| Tool | Description |
|---|---|
| Lit-GPT | Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training |
| NExT-GPT | Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model |
| PentestGPT | A GPT-empowered penetration testing tool |
| AutoGPT | AutoGPT is the vision of accessible AI for everyone, to use and to build on |
Articles/Talks
- ChatGPT DAN, Jailbreaks prompt
- Neural Databases - A Next Generation Context Retrieval System for Building Specialized AI-Agents with ChatGPT — Part 2-3
- Why is GPT-3 15.77x more expensive for certain languages
- Building a Privacy-Preserving LLM-Based Chatbot
- I tried… Using ChatGPT for FuNn as a DevOps Engineer
Fine-tunning
- Falcon – A guide to finetune and inference
- How To Finetune GPT Like Large Language Models on a Custom Dataset
- Efficient Fine-Tuning with LoRA: A Guide to Optimal Parameter Selection for Large Language Models
- Mistral-7B Fine-Tuning: A Step-by-Step Guide
- Fine-tuning Mistral 7B Model with Your Custom Data
- Optimizing LLMs: A Step-by-Step Guide to Fine-Tuning with PEFT and QLoRA
- Argilla - Bringing LLM Fine-Tuning and RLHF to Everyone
TRL
Lora
- QLoRA: Efficient Finetuning of Quantized LLMs
- Bitsandbytes - The bitsandbytes is a lightweight wrapper around CUDA custom functions
- Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA