Trelis

last updated Feb 16th 2024

About

Trelis Research provides:

• Function-calling models.
• Advanced LLM fine-tuning scripts.
• Advanced LLM inference guides.
• Advanced vision fine-tuning scripts.
• Advanced voice/transcription fine-tuning scripts.
• One click LLM API templates

Function-calling Models and Datasets

Get access here

• Fine-tuned models for function calling - from 1.3B to 70B in size, incl. Mixtral, Yi, Deepseek, Llama and more. Collection here
• Dataset to fine-tune models for function calling. Access here
• Scripts to fine-tune models for function calling and structured responses.

ADVANCED Fine-tuning Scripts

Get access here

1. Unsupervised + Supervised Fine-tuning Notebooks
2. Chat fine-tuning scripts
3. Long context fine-tuning scripts
4. Function calling fine-tuning
5. Q&A Dataset Preparation + Cleaning Scripts
6. Scripts to create and use Embeddings
7. Quantization Scripts

ADVANCED Inference

Get access here

• Server setup, API setup and inference guide for open source models.
• Inference for function calling.

ADVANCED Vision

Get access here

• Dataset Preparation
• Fine-tuning Llava and IDEFICS

ADVANCED Transcription

Get access here

• Fine-tuning Whisper on custom datasets
• Dataset Generation
• Evaluation

One-click LLM API/Server Templates

• Check out the full list here
• Includes Llama 70B, Mistral 7B, Mixtral 8x7B and many more