README.md

metadata

language:
  - en
tags:
  - llama-2
pipeline_tag: text-classification
model-index:
  - name: llama-2-13b-guanaco-fp16
    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: 60.92
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Mikael110/llama-2-13b-guanaco-fp16
          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: 83.18
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Mikael110/llama-2-13b-guanaco-fp16
          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: 54.58
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Mikael110/llama-2-13b-guanaco-fp16
          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: 44
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Mikael110/llama-2-13b-guanaco-fp16
          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: 74.9
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Mikael110/llama-2-13b-guanaco-fp16
          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: 11.6
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Mikael110/llama-2-13b-guanaco-fp16
          name: Open LLM Leaderboard

This is a Llama-2 version of Guanaco. It was finetuned from the base Llama-13b model using the official training scripts found in the QLoRA repo. I wanted it to be as faithful as possible and therefore changed nothing in the training script beyond the model it was pointing to. The model prompt is therefore also the same as the original Guanaco model.

This repo contains the merged f16 model. The QLoRA adaptor can be found here.

A 7b version of the model can be found here.

Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	54.86
AI2 Reasoning Challenge (25-Shot)	60.92
HellaSwag (10-Shot)	83.18
MMLU (5-Shot)	54.58
TruthfulQA (0-shot)	44.00
Winogrande (5-shot)	74.90
GSM8k (5-shot)	11.60