last updated Mar 28th 2024
Trelis Research provides:
- Advanced LLM fine-tuning scripts.
- Advanced LLM inference guides.
- Advanced vision fine-tuning scripts.
- Advanced voice/transcription fine-tuning scripts.
- Function-calling models.
- One click LLM API templates
- Unsupervised + Supervised Fine-tuning Notebooks
- Chat fine-tuning scripts
- Long context fine-tuning scripts
- Function calling fine-tuning
- Q&A Dataset Preparation + Cleaning Scripts
- Scripts to create and use Embeddings
- Quantization Scripts
- Server setup, API setup and inference guide for open source models.
- Inference for function calling.
- Dataset Preparation
- Fine-tuning Llava and IDEFICS
- Fine-tuning Whisper on custom datasets
- Dataset Generation
- Evaluation
- 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.
- Check out the full list here
- Includes Llama 70B, Mistral 7B, Mixtral 8x7B and many more
Trelis LTD is run by @RonanKMcGovern
Address: Blackrock, Dublin, Ireland
Irish VAT Number: 3808855SH
Email: Hello @ Trelis [dot] com