All Posts

News

4 minutes

Oct 1, 2024

Introducing Direct Preference Optimization (DPO) Support on OpenPipe

Technical

10 minutes

Aug 28, 2024

Fine-tuning Best Practices Chapter 2: Models

Chapter 2 continuing OpenPipe's fine-tuning best practices series. This chapter focuses specifically on models and the trade-off choices around them to ultimately create the highest performing fine-tuned LLM.

Technical

10 minutes

Aug 1, 2024

Fine-tuning Best Practices Series Introduction and Chapter 1: Training Data

A post introducing a series of articles on LLM fine-tuning best practices, and the first chapter specifically on Training Data best practices.

News

4 minutes

Jul 24, 2024

Announcing Llama 3.1 and GPT-4o Mini fine-tuning through OpenPipe!

News

10 minutes

Jun 20, 2024

OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost

We’re excited to announce a new family of “Mixture of Agents” models optimized for generating synthetic training data.

Technical

5 minutes

May 23, 2024

The Ten Commandments of Fine-Tuning in Prod (a Mastering LLMs Conference Talk)

Here’s the summary and full video of a talk given at Mastering LLMs Conference titled the “Ten Commandments of Fine-Tuning in Prod.”

News

4 minutes

Apr 21, 2024

What we've learned in 3 days of Llama 3

You’ve probably heard about Llama 3, a new open-source LLM. There are 3 variants announced so far: a small 8B parameter model, medium 70B parameter model, and very large 405B parameter model (still in training). I wanted to share the most important things we’ve learned about these models so far.

Basics

5 minutes

Mar 28, 2024

Fine-Tuning in a Nutshell

Hi, I’m David, the CTO of OpenPipe. This is a post for individuals who want to build high-level intuition around fine-tuning.

News

3 minutes

Mar 25, 2024

We Raised $6.7M to Replace GPT-4 with Your Own Fine-Tuned Models

Today I’m excited to announce the close of our $6.7M seed round.

Comparison

4 minutes

Feb 29, 2024

Mixtral Curious? Comparing Mistral 7B and Mixtral for fine-tuning

Evals can be tricky, but we’ve found that LLM-as-judge is the most reliable way to compare two outputs.

Technical

5 minutes

Jan 17, 2024

S-LoRA: Serving Thousands of Models From One GPU for Fun and Profit

S-LoRA describes a set of optimizations for running thousands of separate LLMs simultaneously on the same GPU.

Technical

3 minutes

Jan 4, 2024

Axis Improves Generation Quality and Lowers Costs With Fine Tuning

Axis is a modern platform to help multinational enterprises understand their local markets across the world.

News

3 minutes

Jan 3, 2024

Product Updates December 2023

Hi there! We'd love to share with you some of the recent updates we've made in December

Comparison

7 minutes

Dec 18, 2023

How we built “Mistral 7B Fine-Tune Optimized,” the best 7B model for fine-tuning

Fine-tunes based on our new model are slightly stronger than GPT-4, as measured by GPT-4 itself.

News

3 minutes

Dec 1, 2023

Announcing Automatic Evals for Fine-tuned Models

At OpenPipe we’re building a fully-managed fine-tuning platform for developers.

Technical

8 minutes

Nov 8, 2023

Is AI the Next Crypto? Insights from 2M HN comments

Both crypto and AI have been heavily debated on Hacker News, with discussions going back years.

Technical

2 minutes

Nov 5, 2023

Llama 2 vs Mistral: Believe the Hype

If you’re fine-tuning a task-specific LLM under 34B parameters you should probably be using Mistral.

Technical

2 minutes

Sep 12, 2023

Fine-tune your own Llama 2 to replace GPT-3.5/4

I've been playing around with fine-tuning models for a couple of years, and wanted to share some insights and practical code

Comparison

4 minutes

Aug 28, 2023

From Prompts to Models

OpenPipe lets you capture your existing prompts and completions, and then use them to fine-tune a model specific to your use-case.

Introducing Direct Preference Optimization (DPO) Support on OpenPipe

Introducing Direct Preference Optimization (DPO) Support on OpenPipe

About OpenPipe

OpenPipe is the easiest way to train and deploy your own fine-tuned models. It only takes a few minutes to get started and can save you 25x relative to OpenAI with higher quality.

About OpenPipe

OpenPipe is the easiest way to train and deploy your own fine-tuned models. It only takes a few minutes to get started and can save you 25x relative to OpenAI with higher quality.