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 v1.5 (16k) is fine-tuned from Llama 2 with supervised instruction fine-tuning and linear RoPE scaling.
The training data is around 125K conversations collected from ShareGPT.com. These conversations are packed into sequences that contain 16K tokens each.
See more details in the "Training Details of Vicuna Models" section in the appendix of this
paper
.
Evaluation
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this
paper
and
leaderboard
.
vicuna-7b-v1.5-16k huggingface.co is an AI model on huggingface.co that provides vicuna-7b-v1.5-16k's model effect (), which can be used instantly with this lmsys vicuna-7b-v1.5-16k model. huggingface.co supports a free trial of the vicuna-7b-v1.5-16k model, and also provides paid use of the vicuna-7b-v1.5-16k. Support call vicuna-7b-v1.5-16k model through api, including Node.js, Python, http.
vicuna-7b-v1.5-16k huggingface.co is an online trial and call api platform, which integrates vicuna-7b-v1.5-16k's modeling effects, including api services, and provides a free online trial of vicuna-7b-v1.5-16k, you can try vicuna-7b-v1.5-16k online for free by clicking the link below.
lmsys vicuna-7b-v1.5-16k online free url in huggingface.co:
vicuna-7b-v1.5-16k is an open source model from GitHub that offers a free installation service, and any user can find vicuna-7b-v1.5-16k on GitHub to install. At the same time, huggingface.co provides the effect of vicuna-7b-v1.5-16k install, users can directly use vicuna-7b-v1.5-16k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.