The model may generate biased or offensive content., The model needs fine-tuning for specific tasks.
Additional Notes
The model is part of Intel's initiative for advancements in neural chat technologies.
Supported Languages
en (fluent)
Training Details
Data Sources:
Open-Orca/SlimOrca
Methodology:
Direct Performance Optimization (DPO)
Context Length:
8192
Hardware Used:
Intel Gaudi 2 processor
Safety Evaluation
Ethical Considerations:
Neural-chat-7b-v3-1 can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Responsible Ai Considerations
Fairness:
Mitigation strategies should be implemented to address potential lewd, biased, or offensive outputs.
Accountability:
Developers should perform safety testing before deploying any applications of neural-chat-7b-v3-1.
Input Output
Input Format:
text input with context length 8192 tokens
Accepted Modalities:
text
Output Format:
text
Release Notes
Version:
v3-1
Date:
October, 2023
Notes:
Improved performance metrics and finetuning with Open-Orca/SlimOrca