|
--- |
|
title: README |
|
emoji: 🏢 |
|
colorFrom: red |
|
colorTo: green |
|
sdk: static |
|
pinned: false |
|
tags: [llama, code-llama, jupyter, colab, function calling, QLoRa, fine-tuning, scripts, fine-tuning] |
|
--- |
|
*last updated Sept 24th 2023* |
|
## About |
|
Trelis Research provides tools and tutorials for training, using and deploying large language models. |
|
|
|
## Function-calling Models and Datasets |
|
- [Llama 2 models fine-tuned for function calling, 7B, 13B, 70B, CodeLlama 34B](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2) |
|
- [Dataset to fine-tune models for function calling](https://huggingface.co/datasets/Trelis/function_calling_extended) |
|
|
|
## LLM Server Setup |
|
- [Video: Run Llama 2 on AWS](https://youtu.be/Ror2xOOA-VE) |
|
- [Video: Deploy a Llama API in 5 clicks](https://youtu.be/dJ69gY0qRbg) |
|
- [Purchase access to the GitHub repo](https://buy.stripe.com/9AQ28UcWh4PF1ckeV9) |
|
|
|
## Fine-tuning Scripts |
|
Fine-tune LLMs for style, content or structured responses |
|
- [View the three part YouTube series on embeddings, supervised and unsupervised fine-tuning](https://youtu.be/egnf8L-EUJU) |
|
- [Purchase access to the GitHub repo](https://buy.stripe.com/cN27tef4p2Hx2go4gD) |
|
|
|
## Summarise-Me.com |
|
- [Summarise PDFs and websites up to 60,000 words](https://Summarise-Me.com) |
|
|
|
## Other Top Tutorials |
|
- [Run Code Llama on a Mac with an M1 Chip](https://www.youtube.com/watch?v=a1JlzUzHL-I) |
|
- [Run Llama 2 with 32k Context Length](https://www.youtube.com/watch?v=ELax81LjFhU) |
|
|
