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 |
- Downloads last month
- 699
Model tree for ajibawa-2023/SlimOrca-13B
Datasets used to train ajibawa-2023/SlimOrca-13B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard60.150
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard81.400
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard57.040
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard49.370
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard74.430
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard39.950