https://predibase.com/fine-tuning-index
The research team at Predibase analyzed 700+ fine-tuning experiments using 13 of the most popular open-source models, GPT-3.5/4/4o, and 31 distinct datasets and tasks. We chose open-source models with a max of 7B parameters to ensure that any organization can train the models on low-end GPUs. For evaluation, we utilized task-specific metrics including accuracy, rouge, and HumanEval to assess...
https://predibase.com/lora-land
Hi all, today we're excited to launch LoraLand: 25 fine-tuned mistral-7b models that outperform #gpt4 on task-specific applications ranging from sentiment detection to question answering.All 25 fine-tuned models… - Outperform GPT-4, GPT-3.5-turbo, and mistral-7b-instruct for specific tasks - Are cost-effectively served from a single GPU through LoRAX - Were trained for less than $8 each on...
Ludwig, open-sourced at Uber, makes it easy for any developer to build state-of-the-art ML models with its declarative interface. Ludwig v0.8 is the first low-code open-source framework optimized for efficiently building custom LLMs with your private data.
Hi HN!We are excited to announce the general availability and free trial of Predibase, the first low-code AI platform for developers.Our mission is simple: empower engineering teams everywhere to rapidly build powerful AI-powered applications without needing to learn complex low-level ML frameworks. Using our platform, engineers can train, fine-tune, and operationalize custom models leveraging...