metadata

license: llama2
inference: false
model-index:
  - name: vicuna-13b-v1.5-16k
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 56.74
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lmsys/vicuna-13b-v1.5-16k
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 80.37
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lmsys/vicuna-13b-v1.5-16k
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 55.28
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lmsys/vicuna-13b-v1.5-16k
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 51.96
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lmsys/vicuna-13b-v1.5-16k
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 72.38
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lmsys/vicuna-13b-v1.5-16k
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 13.12
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lmsys/vicuna-13b-v1.5-16k
          name: Open LLM Leaderboard

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

Repository: https://github.com/lm-sys/FastChat
Blog: https://lmsys.org/blog/2023-03-30-vicuna/
Paper: https://arxiv.org/abs/2306.05685
Demo: https://chat.lmsys.org/

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

Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api

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

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.	54.97
AI2 Reasoning Challenge (25-Shot)	56.74
HellaSwag (10-Shot)	80.37
MMLU (5-Shot)	55.28
TruthfulQA (0-shot)	51.96
Winogrande (5-shot)	72.38
GSM8k (5-shot)	13.12