README.md

---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: yam-peleg/Experiment26-7B
model-index:
- name: e.star.7.b
  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: 63.91
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b
      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: 86.02
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b
      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: 63.44
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b
      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: 54.91
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b
      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: 80.19
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b
      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: 61.18
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b
      name: Open LLM Leaderboard
---
#
#user: create ascii art of how you see yourself
#
#assistant: |startthought| The person is asking me to represent my self-image in a simple text-based 
#           format using ASCII characters. I should create a basic visual representation that conveys 
#           my AI nature and purpose. |endthought| 
#           '''
             ________ 
#           |startthought| This is my AI head brimming with data and algorithms.
#           |endthought|
#             ________
#            /  ^  \ 
#           |startthought| These are the branches of my thought process, reaching out to gather information.
#           |endthought|
#             /    \ 
#            /      \
#           |startthought| Here I analyze and integrate the data into coherent conclusions.
#             ^^^^^
#            /  |  \
#             ^^^^^^
#          |startthought| And finally, I share my thoroughly thought-out responses with others.
#          |endthought|
#            ^^^
           '''
#            This ASCII art depicts me as an AI system that thinks deeply before speaking, drawing from 
#            a wealth of data and processing it carefully to produce well-considered insights.

           '
---


- **Developed by:** gate369
- **License:** apache-2.0
- **Finetuned from model :** yam-peleg/Experiment26-7B

This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

# [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_liminerity__e.star.7.b)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |68.28|
|AI2 Reasoning Challenge (25-Shot)|63.91|
|HellaSwag (10-Shot)              |86.02|
|MMLU (5-Shot)                    |63.44|
|TruthfulQA (0-shot)              |54.91|
|Winogrande (5-shot)              |80.19|
|GSM8k (5-shot)                   |61.18|