How to Finetune GPT-Like Large Language Models on a Custom Dataset (lightning.ai)

Screenshot of lightning.ai: How to Finetune GPT-Like Large Language Models on a Custom Dataset

First screen, captured 3 years ago.

Looks similar

Screenshot of lightning.ai: Finetuning LLMs on a Single GPU Using Gradient Accumulation

Finetuning LLMs on a Single GPU Using Gradient Accumulation (lightning.ai)

76 points by ashvardanian 3 years ago | 2 comments

Screenshot of lightning.ai: Takeaways from hundreds of LLM finetuning experiments with LoRA

Takeaways from hundreds of LLM finetuning experiments with LoRA (lightning.ai)

236 points by rasbt 3 years ago | 36 comments

Screenshot of mlops.systems: My finetuned models beat OpenAI's GPT-4

My finetuned models beat OpenAI's GPT-4 (mlops.systems)

376 points by majc2 2 years ago | 86 comments

Blog post evaluating finetuned Mistral, Llama3 and Solar LLMs against OpenAI's GPT-4 on accuracy for structured data extraction from press releases.

fine-tuning llms gpt-4 mistral

Screenshot of efraingaray.com: TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14

TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14 (efraingaray.com)

21 points by EfrainGaray 28 days ago | 9 comments

Blog post benchmarking TabPFN and TabICL foundation models against tuned XGBoost on fourteen tabular datasets, finding the no-training models won all fourteen.

tabpfn tabicl xgboost tabular-data

Screenshot of andlukyane.com: Testing MiniMax M2.7 via API on three real ML and coding workflows

Testing MiniMax M2.7 via API on three real ML and coding workflows (andlukyane.com)

26 points by Artgor 5 months ago | 2 comments

Screenshot of edwarddonner.com: A simulation of me: fine-tuning an LLM on 240k text messages

A simulation of me: fine-tuning an LLM on 240k text messages (edwarddonner.com)

165 points by eddonner 2 years ago | 104 comments

Looks similar

Finetuning LLMs on a Single GPU Using Gradient Accumulation (lightning.ai)

Takeaways from hundreds of LLM finetuning experiments with LoRA (lightning.ai)

My finetuned models beat OpenAI's GPT-4 (mlops.systems)

TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14 (efraingaray.com)

Testing MiniMax M2.7 via API on three real ML and coding workflows (andlukyane.com)

A simulation of me: fine-tuning an LLM on 240k text messages (edwarddonner.com)

Related stories

AI Made Writing Code Easier. It Made Being an Engineer Harder (ivanturkovic.com)

Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning (techcommunity.microsoft.com)

Train Your Own LLM from Scratch (github.com)

Training LLMs from ground zero as a startup (yitay.net)

The new skill in AI is not prompting, it's context engineering (philschmid.de)

We no longer use LangChain for building our AI agents (octomind.dev)