---
language:
- en
license: apache-2.0
datasets:
- Open-Orca/FLAN
model-index:
- name: Llama-Flan-XL2base
  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: 20.65
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
      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: 25.33
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
      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: 23.19
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
      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: 50.58
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
      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: 50.91
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
      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: 0.0
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
      name: Open LLM Leaderboard
---

This is a 230M parameter Small Llama model distilled from the Original one. The model is distilled on OpenOrca's FLAN dataset. The distillation ran over 160000 random samples of FLAN dataset. It is free to download. Also, it is a work in progress, so please use it at your own risk
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Sayan01__Llama-Flan-XL2base)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |28.44|
|AI2 Reasoning Challenge (25-Shot)|20.65|
|HellaSwag (10-Shot)              |25.33|
|MMLU (5-Shot)                    |23.19|
|TruthfulQA (0-shot)              |50.58|
|Winogrande (5-shot)              |50.91|
|GSM8k (5-shot)                   | 0.00|