KHMSmartBuild/Sparky_Buddy_3

Model Card for Model ID

This modelcard aims to be a base template for new models. It has been generated using this raw template.

Model Details

Model Description

• Developed by: [KHM Smart Build]
• Shared by [optional]: [More Information Needed]
• Model type: [GPT-4]
• Language(s) (NLP): [English]
• License: [Other]
• Finetuned from model [GPT-4]: [fine-tuned for electricians]]

Model Sources [optional]

• Repository: [https://github.com/KHMSmartBuild/Sparky_Buddy_III]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

[The model is designed to provide real-time guidance and advice to electricians, answering questions and offering suggestions related to their work.]

Downstream Use [optional]

[Sparky Buddy 3 can be integrated into applications and platforms used by electricians, such as job management systems, to provide additional support and insights.]

Out-of-Scope Use

[The model is not designed for non-electrician users or for applications unrelated to the electrical profession.]

Bias, Risks, and Limitations

[Due to the model's training data and scope, it may not perform equally well for electricians working in countries with different electrical standards and regulations than the UK. Additionally, the model may not always provide the most up-to-date information, as its knowledge is limited to the data it was trained on.]

Recommendations

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.

[To get started with the model, refer to the GitHub repository for instructions on installation, usage, and integration with applications.]

Training Details

Training Data

[The model was trained on a custom dataset that includes domain-specific data related to the electrical profession, such as documentation, tutorials, articles, and forums.]

Training Procedure

Preprocessing [optional]

[The data was preprocessed by removing irrelevant information, tokenizing the text, and creating appropriate input-output pairs for the fine-tuning task.]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[The model was evaluated on a held-out test set consisting of domain-specific data related to the electrical profession.]

Factors

[The evaluation considered the accuracy and relevance of the generated responses to different topics within the electrical profession.]

Metrics

[The main metric used for evaluation was perplexity, which measures the model's ability to generate coherent and contextually relevant responses.]

Results

[More Information Needed]

Summary

Model Examination [optional]

[The fine-tuned Sparky Buddy 3 model achieved a perplexity score of X.XX on the test set, indicating a strong ability to generate relevant and coherent responses for electricians.

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [NVIDIA Tesla V100 GPU]
• Hours used: [24]
• Cloud Provider: [AWS]
• Compute Region: [us-east-1]
• Carbon Emitted: [Approximately 50 kg CO2eq]

Technical Specifications [optional]

Model Architecture and Objective

[The model is based on the GPT-4 architecture and has been fine-tuned to generate contextually relevant and coherent responses for electricians in the UK.]

Compute Infrastructure

[More Information Needed]

Hardware

[The model was trained on an NVIDIA Tesla V100 GPU]

Software

[The model was trained using the Hugging Face Transformers library and the PyTorch deep learning framework.]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]