We recently held a #Ludwig community #hackathon and we're excited to share the contributions from one of our winners, Iuliana Stroia and her project, Assessing #Health Data w/ #ML Youtube: https://
pbase.ai/43pLSFP Notebook from the project:
@predibase
-
Ludwig Hackathon Winner: ML Health Data Assessment Project
By
–
-
LoRA Land’s Mistral-7B Models Cut Inference Costs Significantly
By
–
LoRA Land's 27 fine-tuned #opensource #mistral-7b #LLMs no only rival #GPT-4, but they're also very cost-effective! Assuming 2M tokens (90% input; 10% output) per adapter per day, you can cut inference costs by 45%-65% vs. GPT-3.5 Turbo and 97%-98% vs. GPT-4 Turbo
-
Fine-Tuning Newsletter: LoRA Adapters Outperforming GPT-4
By
–
Read the latest edition of our Fine-Tuned newsletter! We cover: #LoRA Land: 25 #finetuned open-source adapters that outperform GPT-4 [Webinar] 5 Reasons Why #Adapters are the Future of LLMs [eBook] Definitive Guide to Fine-Tuning #LLMs
And more! -
Fine-tuning and Structured Generation for Reliable JSON Output with LLMs
By
–
Fine-tuning + structured generation = improved #JSON generation with #LLMs! Check out our blog and benchmarks to learn how you can reliably output JSON with open-source frameworks #LoRAX and #Outlines, and Predibase.
-
LoRAX Open Source Framework Reaches 1000 Stars
By
–
LoRAX, our #opensource framework for cost efficiently serving many #finetuned LLMs on as single GPU, recently joined the 1k club! Check out #LoRA Land to see it in action: https://
pbase.ai/3SXxeAL Download #LoRAX and give it a star if you like it: https://
pbase.ai/49vp89y -
Predibase Launches 25+ Open-Source Fine-Tuned Adapters Rivaling GPT-4
By
–
Last week we launched 25+ #opensource fine-tuned #adapters that rival #GPT4. Join @justinxzhao & our team of experts to hear how they did it! We'll share all of our insights from fine-tuning #Mistral for a broad set of #LLM use cases! Save your spot https://
pbase.ai/42Xsgsm -
Fine-tune Google’s Gemma7B efficiently with Ludwig AI
By
–
Off the shelf is good, fine-tuned is better. Here's everything you need to #efficiently fine-tune @Google
's #Gemma7B for your task. Best of all, you can do it with @ludwig_ai
, the open-source declarative framework for building custom #LLMs. -
7 Essential Things to Know About Fine-tuning LLMs
By
–
Getting started #finetuning? Here are 7 things you need to know We gathered the most common questions from helping our customers fine-tune 1000s of #LLMs and pulled together a blog with our answers to help share the knowledge!
-
Ludwig v0.10.0 Released with Gemma, U-Net and Phi2 Support
By
–
Announcing #Ludwig v0.10.0: Support for @Google
's #Gemma 2B / 7B Added U-Net encoder-decoder and image output feature Added #Phi2 to model presets Support for prompt lookup decoding during generation Multiple bug fixes Full release notes: https://
pbase.ai/49JwFkO -
LoRAX v0.8 Release: JSON Structured Outputs Support Added
By
–
New minor release for #LoRAX, our open-source framework for serving 100s of #LLMs on a single #GPU:
LoRAX v0.8 now supports structured outputs (#JSON mode) courtesy of #Outlines!