(function() { var utmInheritingDomain = "appstore.com", utmRegExp = /(&|\?)utm_[A-Za-z]+=[A-Za-z0-9]+/gi, links = document.getElementsByTagName("a"), utms = [ "utm_medium={{URL - utm_medium}}", "utm_source={{URL - utm_source}}", "utm_campaign={{URL - utm_campaign}}" ]; for (var index = 0; index < links.length; index += 1) { var tempLink = links[index].href, tempParts; if (tempLink.indexOf(utmInheritingDomain) > 0) { tempLink = tempLink.replace(utmRegExp, ""); tempParts = tempLink.split("#"); if (tempParts[0].indexOf("?") < 0 ) { tempParts[0] += "?" + utms.join("&"); } else { tempParts[0] += "&" + utms.join("&"); } tempLink = tempParts.join("#"); } links[index].href = tempLink; } }());

Friendli Fine-Tuning:
Streamline from fine-tuning to serving

Try fine-tuningNeed expert help?

Optimize generative AI performance by customizing models

Unlock your business’s potential with fine-tuned models. Use your data to achieve precise, industry-specific outputs, enhancing performance while saving time and resources.

Fine-tuning pre-trained models with your data

Looking for fine-tuning experts?

Experience a fully hands-off model training service. Our AI experts handle everything from model selection and dataset preparation to fine-tuning and deployment, ensuring a seamless process for you.

Book demo

Fine-tuning

Why fine-tuning?

Optimize open-source or pre-trained custom models with your enterprise data to specialize particular domains or tasks.

Cost, time and dataset efficiency

Leverage smaller, cost-effective models to outperform expensive ones in certain domains.

Why choose Friendli Fine-Tuning?

Parameter-efficient fine-tuning

Achieve rapid model customization with high-quality results while significantly reducing computational resource requirements.

Dedicated expert support

Our team of AI experts will work with you on the entire process of fine-tuning, ensuring that your model is tailored to meet your unique needs efficiently and effectively.

Optimized multi-GPU training

Harness the power of multiple GPUs to speed up the fine-tuning process.

Effortlessly deploy your fine-tuned models

Fine-tune and deploy

Friendli Suite not only enables you to easily fine-tune your models but also streamlines the deployment process. You can run your fine-tuned models on autopilot with just a few clicks with Friendli Dedicated Endpoints or gain maximum control and privacy in your own private environment with Friendli Container.

This seamless process ensures high performance and cost-efficiency for your operations.

Dedicated EndpointsContainer

Start your fine-tuning project now for your custom model

Try nowView supported models
Llama 3.1

Llama 3.1

Llama 3

Llama 3

Mistral

Mistral

Mixtral

Mixtral

Qwen 2.5

Qwen 2.5

Gemma 2

Gemma 2

Phi 3.5

Phi 3.5

and any LLM/LMM or your custom model

Serve a fine-tuned model in one-click

01

Friendli Dedicated Endpoints

Seamlessly deploy your fine-tuned model right away in Friendli Dedicated Endpoints

Learn more

02

Friendli Container

Serve your fine-tuned model within your own private environment for maximum security and privacy

Learn more