Devvret Rishi

Devvret Rishi

PredibasePredibase
Co-founder of Predibase

3 Upvotes

Predibase Reinforcement Fine-Tuning
Predibase Reinforcement Fine-TuningLLM reinforcement fine-tuning platform to improve LLM output
Ludwig 0.8
Ludwig 0.8Build and fine-tune custom LLMs on your private data
LoraLand25 fine-tuned Mistral-7b models that outperform GPT-4