| Model Type | | INT4 inference model, causal language model |
|
| Use Cases |
| Areas: | | Research, Commercial Applications |
|
| Applications: | |
| Primary Use Cases: | | Text generation in natural language processing |
|
| Limitations: | | May generate factually incorrect, lewd, biased, or otherwise offensive outputs. |
|
|
| Additional Notes | | The model employs INT4 quantization, which may result in slight accuracy trade-offs. Model developed using Intel's auto-round tool. |
|
| Supported Languages | |
| Responsible Ai Considerations |
| Fairness: | | The model may generate biased or offensive outputs. |
|
| Transparency: | | Developers should perform safety testing before deployment. |
|
| Accountability: | | Model users should be aware of risks and biases. |
|
|
| Input Output |
| Input Format: | |
| Accepted Modalities: | |
| Output Format: | |
| Performance Tips: | | Consider using the latest version of the Intel Extension for Transformers for optimal performance. |
|
|
