SlimOrca-13B/README.md

language, license, datasets, model-index

language	license	datasets	model-index
en	cc-by-nc-nd-4.0	Open-Orca/SlimOrca ajibawa-2023/SlimOrca-ShareGPT	name results SlimOrca-13B 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 60.15 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/SlimOrca-13B 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 81.4 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/SlimOrca-13B 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 57.04 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/SlimOrca-13B 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 49.37 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/SlimOrca-13B 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 74.43 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/SlimOrca-13B 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 39.95 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/SlimOrca-13B Open LLM Leaderboard

SlimOrca-13B: A General Purpose Intelligent Model

This Model is trained on refined version of SlimOrca made available by Open-Orca team. The idea was to check how this Model will perform in the absence of "system" prompt/instruction. This Model is very good in various types of General Purpose content generation such as Q&A (including multiple choice), Articles from Summary, Sentiment Analysis, Context & Hypothesis, Reviews, Erotic story generation etc. It can also generate Uncensored content. Kindly be careful while generating Uncensored content as you will be responsible for what you generate.

It is trained on 517981 set of conversations. Each set having 2 conversations. I have shared this data.

All the credit goes to the Open-Orca team for releasing SlimOrca dataset.

Training: Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took almost 11 Days. DeepSpeed codebase was used for training purpose. Entire data is trained on Llama-2 by Meta.

This is a full fine tuned model. Links for quantized models are given below.

GPTQ GGML & AWQ

GPTQ: Link

GGUF: Link

AWQ: Link

Special Thanks to TheBloke for making these models available.

Example Prompt:

This is a conversation with your Assistant. It is a computer program designed to help you with various tasks such as answering questions, providing recommendations, and helping with decision making. You can ask it anything you want and it will do its best to give you accurate and relevant information.

Context
You are a helpful AI assistant.

USER: <prompt>
ASSISTANT:

You can modify above Prompt as per your requirement. I have used ShareGPT/Vicuna format v1.1 .

I want to say special Thanks to the Open Source community for helping & guiding me to better understand the AI/Model development.

Thank you for your love & support.

Example Output

Example 1

Example 2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	60.39
AI2 Reasoning Challenge (25-Shot)	60.15
HellaSwag (10-Shot)	81.40
MMLU (5-Shot)	57.04
TruthfulQA (0-shot)	49.37
Winogrande (5-shot)	74.43
GSM8k (5-shot)	39.95