Vicuna
An open-source conversational large language model fine-tuned from LLaMA, commonly used as a research baseline.
Timeline (last 90 days)
Relative to the Vicuna autoregressive baseline, HAD-VLM reduces error by 21.4%–37.6% on the four EchoNet-LVH tasks.
After LLaMA was open-sourced, the community rapidly produced a large number of derivative models such as Alpaca and Vicuna.
Open-source projects led by Berkeley include the Caffe deep learning framework, the Ray distributed computing framework, and the large language model projects Vicuna and LMSYS Chatbot Arena.
Meta的Llama系列作为开源模型对齐程度较轻，催生了Vicuna、Alpaca等数以千计的衍生模型
All Facts (4)
Relative to the Vicuna autoregressive baseline, HAD-VLM reduces error by 21.4%–37.6% on the four EchoNet-LVH tasks.
50%UnverifiedAfter LLaMA was open-sourced, the community rapidly produced a large number of derivative models such as Alpaca and Vicuna.
50%UnverifiedOpen-source projects led by Berkeley include the Caffe deep learning framework, the Ray distributed computing framework, and the large language model projects Vicuna and LMSYS Chatbot Arena.
50%UnverifiedMeta的Llama系列作为开源模型对齐程度较轻，催生了Vicuna、Alpaca等数以千计的衍生模型
50%