---
title: README
emoji: 🏢
colorFrom: blue
colorTo: green
sdk: static
pinned: true
tags:
- function calling
- long context
- mistral
- deepseek
- yi
- code-llama
- quantization
- SFT
- fine-tuning
---
*last updated Nov 19th 2023*
## About
Trelis Research provides specialised fine-tuned models AND fine-tuning scripts.

## Function-calling Models and Datasets
- [Fine-tuned models for function calling - from 1.3B to 70B in size, incl. Yi, Deepseek, Llama and more](https://trelis.com/function-calling/)
- [Dataset to fine-tune models for function calling](https://huggingface.co/datasets/Trelis/function_calling_extended)
- [Scripts to fine-tune models for function calling and structured responses](https://trelis.com/function-calling/)

## ADVANCED Fine-tuning Scripts

[Learn more here](https://trelis.com/advanced-fine-tuning-scripts/)

1. Unsupervised + Supervised Fine-tuning Notebooks
1. Q&A Dataset Preparation + Cleaning Scripts
1. Scripts to create and use Embeddings
1. Quantization Scripts
1. Chat fine-tuning Scripts

## LLM Server Setup
- Server setup and inference guide for open source models.
- Inference for function calling.
- [Video: Run Llama 2 on AWS](https://youtu.be/Ror2xOOA-VE)
- [Video: Deploy a Llama API in 5 clicks](https://youtu.be/dJ69gY0qRbg)
- [Learn more here](https://trelis.com/enterprise-server-api-and-inference-guide/)

## One-click LLM API/Server Templates
- [Runpod affiliate link](https://tinyurl.com/yjxbdc9w)
- [Llama 2 70B](https://tinyurl.com/2szykc6m)

## 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)