Model Type | |
Use Cases |
Areas: | English and Chinese Multilingual Applications |
|
Applications: | |
Primary Use Cases: | Provides helpful and logical assistance |
|
Limitations: | Inherent limitations include the potential for erroneous, offensive, or undesirable outputs. Not suitable for critical or high-stakes scenarios. |
|
Considerations: | Do not use in situations leading to personal injury, property damage, or significant losses. |
|
|
Additional Notes | Quantized in the unsloth way. |
|
Supported Languages | English (proficient), Chinese (proficient) |
|
Training Details |
Data Sources: | |
Methodology: | Quantized in the unsloth way |
|
|
Responsible Ai Considerations |
Fairness: | Ensure responses are socially unbiased and positive in nature. |
|
Accountability: | OpenBuddy team from https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy |
|
Mitigation Strategies: | OpenBuddy cannot access the internet and is designed to avoid harmful content. |
|
|
Input Output |
Input Format: | <|role|><role type><|says|><content><|end|> |
|
Accepted Modalities: | |
Output Format: | Textual conversational outputs |
|
Performance Tips: | Use the fast tokenizer from `transformers`. |
|
|