Model Card for Llama-Q4V

Llama-Q4V is a quantized and voice-optimized version of Llama-3.1-8B-Instruct, and is the core LLM for Ai Tag, an open source $20 competitor to Humane's Ai Pin.

Model Details

Model Description

• Developed, Funded, and Shared by: Jacob Leuthardt
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

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.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Llama-Q4V was evaluated on HellaSwag, GLUE, and TriviaQA

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
- cola	1	none	0	mcc	↑	0.0409	±	0.0323
glue	N/A	none	0	acc	↑	0.5002	±	0.0019
		none	0	f1	↑	0.5789	±	0.0026
		none	0	mcc	↑	0.0409	±	0.0323
hellaswag	1	none	0	acc	↑	0.5849	±	0.0049
		none	0	acc_norm	↑	0.7846	±	0.0041
- mnli	1	none	0	acc	↑	0.5200	±	0.0050
- mnli_mismatch	1	none	0	acc	↑	0.5098	±	0.0050
- mrpc	1	none	0	acc	↑	0.6887	±	0.0230
		none	0	f1	↑	0.8113	±	0.0165
- qnli	1	none	0	acc	↑	0.5032	±	0.0068
- qqp	2	none	0	acc	↑	0.4816	±	0.0025
		none	0	f1	↑	0.5765	±	0.0027
- rte	1	none	0	acc	↑	0.6679	±	0.0283
- sst2	1	none	0	acc	↑	0.8612	±	0.0117
triviaqa	3	remove_whitespace	0	exact_match	↑	0.4962	±	0.0037
- wnli	2	none	0	acc	↑	0.6197	±	0.0580

Groups	Version	Filter	n-shot	Metric		Value		Stderr
glue	N/A	none	0	acc	↑	0.5002	±	0.0019
		none	0	f1	↑	0.5789	±	0.0026
		none	0	mcc	↑	0.0409	±	0.0323

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

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

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

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]