Announcing #Ludwig v0.9.3! Support for microsoft/phi-2 Ensure correct padding token for #Phi and Pythia models Cast LLMEncoder output to torch.float32, freeze final layer at init Enable IA3 adapters Add batch size tuning for #LLMs https://
pbase.ai/3HAOxCs
@predibase
-
Ludwig v0.9.3 Release: Phi-2 Support and LLM Improvements
By
–
-
Own Your AI Models: Open Source Over Proprietary Solutions
By
–
#OpenAI is a great place to start, but not finish. You deserve to own your #models (that's your IP!) and you can get better performance at a fraction of the cost with #opensource. Check out @devvret_rishi
's article with @Dataversity to learn more. -
Private Task-Specific LLMs: The Future of AI Economics
By
–
Same page! Private, smaller, task specific LLMs fine-tuned on open-source models are the future – why pay to rent expensive, general purpose LLMs from commercial vendors. And, with new serving architectures like LoRAX (
http://
loraexchange.ai) its becoming very economical. -
Fine-tuning Discussion: The Future of Smaller Open-Source LLMs
By
–
Thanks for having @devvret_rishi on to discuss all things fine-tuning and why smaller faster open-source #LLMs are the future!
-
Fine-tune Zephyr-7B for Customer Support Classification
By
–
Join our live tutorial and demo on how to #finetune #Zephyr-7B for a real-world AI use case: analyzing + classifying customer support calls. You'll also learn how fine-tuned #opensource #LLMs can outperform commercial LLMs at a fraction of the cost. https://
pbase.ai/42d0O9x -
Predibase Reduces Deep Learning Model Development Time from Months to Minutes
By
–
"The time it takes to build production #deeplearning models on top of Snowflake has been reduced from months to minutes and at a fraction of the cost with Predibase" –
@tradeparadigm Check out our latest blog to learn more about this cool project: https://
pbase.ai/4b0haWW -
Fine-Tuned Newsletter: LoRAX, Open Source, and LLaMA2 Updates
By
–
ICYMI, here's the 1st ed. of our newsletter Fine-Tuned! Check out our most popular blogs, webinars and latest product / OSS updates:
– #LoRAX
– Graduate from #OpenAI to #OpenSource
– How to #finetune #llama2-70b
Read more: https://
pbase.ai/3HAhgqF Sign-up: https://
pbase.ai/48V37jS -
Ludwig v0.9.2 Released with New Features and Improvements
By
–
Announcing #Ludwig v0.9.2! This release introduces several capabilities and fixes: Per-step token utilization to tensorboard and progress tracker Default LoRA target modules for #Mixtral Support for exporting models to Carton https://
pbase.ai/3vI8SCW -
Fine-tune Zephyr-7B for Customer Service Intent Detection
By
–
ICYMI: We recently released a new #LLM tutorial for #finetuning open-source #Zephyr-7B to determine the intent of customer service tickets. Sample data, code and notebooks included. Check it out to get started! https://
pbase.ai/3vCIdr3 -
12 Best Practices for Distilling Smaller Language Models from GPT
By
–
Ready to graduate from #OpenAI to #opensource? Check out our definitive list of 12 best practices for distilling smaller language models from #GPT.