Quantization made by Richard Erkhov.
This model has been pruned to 30% sparsity using the
Wanda pruning method on attention layers. This method requires no retraining or weight updates and still achieves competitive performance. A link to the base model can be found
here.
Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
The primary use of Vicuna is research on large language models and chatbots.
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning.
The training data is around 125K conversations collected from ShareGPT.com.
See more details in the "Training Details of Vicuna Models" section in the appendix of this
paper.
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this
paper and
leaderboard.
