language, license, tags, base_model, model-index

language	license	tags	base_model	model-index
en	apache-2.0	text-generation-inference transformers unsloth mistral trl	yam-peleg/Experiment26-7B	name results e.star.7.b task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 63.91 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 86.02 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 63.44 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 54.91 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 80.19 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 61.18 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/e.star.7.b 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 and Huggingface's TRL library.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

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