85 lines
2.8 KiB
Markdown
85 lines
2.8 KiB
Markdown
---
|
|
license: apache-2.0
|
|
datasets:
|
|
- the_pile
|
|
- guanaco/guanaco
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# Model Card for Cerebras 1.3b Dollyfied.
|
|
|
|
This is a finetuned model of Cerebras 1.3b model. using DataBricksLabs Dolly Framework
|
|
|
|
## Model Details
|
|
|
|
### Model Description
|
|
|
|
This is a finetuned version of cerebras' 1.3Billion paramater model that has been trained to follow instructions.
|
|
|
|
It was accomplished using DataBricks Dolly training tools, and was trained for 2 epochs.
|
|
|
|
- **Developed by:** Finetuned by Corianas (me) using open source tools
|
|
- **Shared by [optional]:** [More Information Needed]
|
|
- **Model type:** [More Information Needed]
|
|
- **Language(s) (NLP):** EN
|
|
- **License:** cc-by-nc-4.0
|
|
- **Finetuned from model:** https://huggingface.co/cerebras/Cerebras-GPT-111m
|
|
- **Finetuned using:** https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html
|
|
|
|
## Uses
|
|
|
|
This is a simple GPT chatbot that has been finetuned to understand instructions.
|
|
Its knowledge about facts about the world is should be considered suspect at best.
|
|
|
|
### Direct Use
|
|
|
|
If you have a use you put it to, Please let me know.
|
|
|
|
[More Information Needed]
|
|
|
|
### Downstream Use [optional]
|
|
|
|
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
|
|
|
[More Information Needed]
|
|
|
|
### Out-of-Scope Use
|
|
|
|
Any form of use where any form of accuracy is needed.
|
|
FOR THE LOVE OF GOD DO NOT FOLLOW MEDICAL ADVICE FROM THIS.
|
|
or financial advice.
|
|
|
|
[More Information Needed]
|
|
|
|
## Bias, Risks, and Limitations
|
|
|
|
Limitations... Yes, I am sure there are so so many.
|
|
|
|
|
|
## Environmental Impact
|
|
|
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
|
|
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
|
|
|
- **Hardware Type:** 8xA100s (accomplished while I was downloading the model I was actually training.)
|
|
- **Minutes used:** 17
|
|
- **Cloud Provider:** LambdaGPU
|
|
- **Compute Region:** USA
|
|
- **Carbon Emitted:** [More Information Needed]
|
|
|
|
# [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_Corianas__Quokka_1.3b)
|
|
|
|
| Metric | Value |
|
|
|-----------------------|---------------------------|
|
|
| Avg. | 27.1 |
|
|
| ARC (25-shot) | 27.73 |
|
|
| HellaSwag (10-shot) | 37.91 |
|
|
| MMLU (5-shot) | 26.66 |
|
|
| TruthfulQA (0-shot) | 40.14 |
|
|
| Winogrande (5-shot) | 52.72 |
|
|
| GSM8K (5-shot) | 0.0 |
|
|
| DROP (3-shot) | 4.54 |
|