H2O LLM Studio, no-code GUI, fine-tuning LLMs
-
Welcome to H2O LLM Studio, a framework and no-code GUI designed for
fine-tuning state-of-the-art large language models (LLMs).
https://github.com/h2oai/h2o-llmstudio/
With H2O LLM Studio, you can
- easily and effectively fine-tune LLMs without the need for any coding experience.
- use a graphic user interface (GUI) specially designed for large language models.
- finetune any LLM using a large variety of hyperparameters.
- use recent finetuning techniques such as Low-Rank Adaptation (LoRA) and 8-bit model training with a low memory footprint.
- use advanced evaluation metrics to judge generated answers by the model.
- track and compare your model performance visually. In addition, Neptune integration can be used.
- chat with your model and get instant feedback on your model performance.
- easily export your model to the Hugging Face Hub and share it with the community.
Quickstart
For questions, discussing, or just hanging out, come and join Discord!
We offer several ways of getting started quickly.
Using CLI for fine-tuning LLMs:
-
Well done on finding this one, @robi ! I was about to suggest it myself.
How did I miss it here?https://huggingface.co/h2oai
https://gpt-gm.h2o.ai/There is a video of a chap using it with Falcon 40b here:
https://invidious.io.lol/watch?v=H8Dx-iUY49s&quality=dashI can't seem to find that model there, at the moment. https://falcon.h2o.ai/
Near the very end, you can see him upload / link by URL a document which he then interrogates using the AI.
-
Welcome to H2O LLM Studio, a framework and no-code GUI designed for
fine-tuning state-of-the-art large language models (LLMs).
https://github.com/h2oai/h2o-llmstudio/
With H2O LLM Studio, you can
- easily and effectively fine-tune LLMs without the need for any coding experience.
- use a graphic user interface (GUI) specially designed for large language models.
- finetune any LLM using a large variety of hyperparameters.
- use recent finetuning techniques such as Low-Rank Adaptation (LoRA) and 8-bit model training with a low memory footprint.
- use advanced evaluation metrics to judge generated answers by the model.
- track and compare your model performance visually. In addition, Neptune integration can be used.
- chat with your model and get instant feedback on your model performance.
- easily export your model to the Hugging Face Hub and share it with the community.
Quickstart
For questions, discussing, or just hanging out, come and join Discord!
We offer several ways of getting started quickly.
Using CLI for fine-tuning LLMs:
-
@LoudLemur no different than ones you would use to run the other projects that can run models with.
