Llama-2 chat, Mistral, Zephyr, and Open Hermes 2.5 are great 7B models for fine-tuning. I have experimented with these and was able to get great results for summarization, and RAG.
Llama-2 chat, Mistral, Zephyr, and Open Hermes 2.5 are great 7B models for fine-tuning. I have experimented with these and was able to get great results for summarization, and RAG.