Haven (YC S23) – Quickly iterate when fine-tuning open-source LLMs
Demo Video: https://www.youtube.com/watch?v=XpyVKUyt7k8 Hey all! A friend and I have been building projects with open-source LLMs for a while now (originally for other project ideas) and found that quickly iterating with different fine-tuning datasets is super hard. Training a model, setting up some inference code to try out the model and then going back and forth took 90% of our time. That’s why we built Haven, a service to quickly try out different fine-tuning datasets and base-models. Going from uploading a dataset to chatting with the resulting model now takes less than 5…
In plain words
Haven is a service that streamlines fine-tuning of open-source large language models. It allows developers to upload datasets and test different fine-tuned models in minutes rather than hours, reducing iteration time significantly. The platform uses low-rank adapters to keep model changes small and enables efficient hosting of multiple fine-tuned variants. Haven is designed for machine learning engineers and developers who frequently experiment with custom LLM fine-tuning.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Demo Video: https://www.youtube.com/watch?v=XpyVKUyt7k8 Hey all! A friend and I have been building projects with open-source LLMs for a while now (originally for other project ideas) and found that quickly iterating with different fine-tuning datasets is super hard. Training a model, setting up some inference code to try out the model and then going back and forth took 90% of our time. That’s why we built Haven, a service to quickly try out different fine-tuning datasets and base-models. Going from uploading a dataset to chatting with the resulting model now takes less than 5 minutes (using a reasonably sized dataset). We fine-tune the models using low-rank adapters, which not only means that the changes made to the model are very small (only 30mb for a 7b parameter LLM), it also allows us to host many fine-tuned models very efficiently by hot swapping adapters on demand. This helped us reduce cold-start times to below one second and makes it possible for us to host a single trained model for a few dollars per month. [Research has shown](https://arxiv.org/pdf/2305.14314.pdf) that low-rank fine-tuning performance stays almost on-par with full fine-tuning. We charge between $0.004/1k training tokens, and after signing up, you get $5 in free credits. You can export all the models to Huggingface. Right now we support Llama-2 and Zephyr (which is itself a fine-tune of Mistral) as base models. We’re gonna add some more soon. We hope you find this useful and we would love your feedback!
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
Launched alongside, November 2023
the whole month →
Discover & book top creators to promote your product
Growth · 2023 · passionfroot.me
