#finetuningllms — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #finetuningllms, aggregated by home.social.
-
A practical map of LLM post-training: how SFT, reward models, RL (PPO, GRPO), DPO, and RLVR fit together, and why a reward model is not RL. https://hackernoon.com/how-llms-are-trained-after-pretraining-sft-reward-models-and-rl-without-the-alphabet-soup #finetuningllms
-
https://www.tkhunt.com/2285216/ Hermes Agent: The Self-Improving AI That Learns You #AgenticAi #AI #ArtificialIntelligence #FineTuningLLMs #GPT4 #Llama #LLMs #PromptEngineer #PromptEngineering #エージェント型AI #人工知能
-
Learn the difference between fine-tuning a large language model and using Retrieval-Augmented Generation (RAG). https://hackernoon.com/fine-tuning-vs-rag-how-to-choose-the-right-approach-to-training-llms-on-your-data #finetuningllms