README.md

---
license: apache-2.0
model-index:
- name: DopeyTinyLlama-1.1B-v1
  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: 38.4
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vihangd/DopeyTinyLlama-1.1B-v1
      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: 63.49
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vihangd/DopeyTinyLlama-1.1B-v1
      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: 25.76
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vihangd/DopeyTinyLlama-1.1B-v1
      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: 37.36
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vihangd/DopeyTinyLlama-1.1B-v1
      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: 73.4
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vihangd/DopeyTinyLlama-1.1B-v1
      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: 1.82
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vihangd/DopeyTinyLlama-1.1B-v1
      name: Open LLM Leaderboard
---
<p><h1> DopeyTinyLlama-1.1B-v1 </h1></p>
An experimental DPO finetune of SmarTinyLlama with Alpaca-QLoRA

<h2> Datasets </h2>
Trained on bagel style DPO datasets

<p><h2> Prompt Template </h2></p>
Uses chatml style prompt template
<br><br>
# [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_vihangd__DopeyTinyLlama-1.1B-v1)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |40.04|
|AI2 Reasoning Challenge (25-Shot)|38.40|
|HellaSwag (10-Shot)              |63.49|
|MMLU (5-Shot)                    |25.76|
|TruthfulQA (0-shot)              |37.36|
|Winogrande (5-shot)              |73.40|
|GSM8k (5-shot)                   | 1.82|