README.md

---
license: cc-by-nc-4.0
datasets:
- tatsu-lab/alpaca
language:
- en
---
# Model Card for Cerebras 1.3b Dollyfied.

This is a finetuned model of Cerebras 1.3B model using DataBricksLabs Dolly Framework

# Example output:
Instruction: Write a love letter to Edgar Allan Poe.

Edgar Allan Poe is here again, with a brand new treasure of tales for you to enjoy. First, a man's life as a fallen angel, then his lonely falls into the sea, and finally a journey through the wild, exciting lands of the American West. He also carries a mysterious message for us: never stop searching for our own sweet. Thank you, Edgar Allan Poe!

-----------

Instruction: Write a tweet announcing Dolly, a large language model from Databricks.

Dolly a brand new model from Databricks that has been thoroughly validated and improved with feedback from experts and users! #databricks #languagemodels #databrickslanguage

-----------

Instruction: I'm selling my Nikon D-750, write a short blurb for my ad.

We bring you the revolutionary Nikon D-750 - the perfect camera for any shoot. With the Nikon D-750, you'll be able to achieve stunning images with state-of-the-art features and brilliant images. The Nikon D-750 is the perfect camera for everyday work, and it produces brilliant, vibrant images with spectacular clarity. Whether you’re a professional, a hobbyist, or an enthusiast, the Nikon D-750 is the perfect camera for you. Get yours today!

-----------

Instruction: Explain to me the difference between nuclear fission and fusion.

Nuclear fission and fusion are both processes that use nuclear material and energy to generate heat. Fission, which occurs at high enough temperatures, produces either a proton or a neutron with the same energy level. Fusion, on the other hand, relies on a hydrogen atom and is considered to be the most stable process. Nuclear fission and fusion produce different amounts of heat, which is why nuclear fusion can be used to generate heat energy for a variety of applications.

-----------

Instruction: Give me a list of 5 science fiction books I should read next.

1. The coming of the Red Planet by Guy Adams
2. The Hitchhiker's Guide to the Galaxy by Douglas Adams
3. Out of the Ashes by Douglas Adams
4. The Hitchhiker's Guide to the Galaxy episode "The Ancient of Days"
5. Icy Girls by J.R.R. Tolkien

-----------
## 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.

- **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-1.3b
- **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

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[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

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

## How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

## Training Details

### Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure 

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Data Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## 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:** 8xA100
- **Hours used:** 30mins
- **Cloud Provider:** Lambda GPU

## Technical Specifications [optional]

### Model Architecture and Objective

GPT2 Cerebras-GPT	1.3B	
Layers	24   
n_embd 2048 
Heads  16

#### Hardware

8xA100s

#### Software

https://github.com/databrickslabs/dolly



## Model Card Contact

[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__1.3b)

| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 27.02   |
| ARC (25-shot)         | 27.3          |
| HellaSwag (10-shot)   | 38.3    |
| MMLU (5-shot)         | 26.77         |
| TruthfulQA (0-shot)   | 39.02   |
| Winogrande (5-shot)   | 53.04   |
| GSM8K (5-shot)        | 0.15        |
| DROP (3-shot)         | 4.57         |