vicuna-7b-v1.5-16k / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
18cb4ce
|
raw
history blame
2.73 kB
metadata
inference: false
license: llama2

Vicuna Model Card

Model Details

Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.

  • Developed by: LMSYS
  • Model type: An auto-regressive language model based on the transformer architecture
  • License: Llama 2 Community License Agreement
  • Finetuned from model: Llama 2

Model Sources

Uses

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.

How to Get Started with the Model

Training Details

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

Evaluation Results

Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this paper and leaderboard.

Difference between different versions of Vicuna

See vicuna_weights_version.md

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 45.24
ARC (25-shot) 54.69
HellaSwag (10-shot) 77.32
MMLU (5-shot) 49.51
TruthfulQA (0-shot) 50.41
Winogrande (5-shot) 71.11
GSM8K (5-shot) 6.44
DROP (3-shot) 7.16