This is the PC version of this model for AMD/NVIDA GPUs.
Linux Version here (https://huggingface.co/jetro30087/vicuna-Wizard-7B-Uncensored-linux-q4f16_0)
Android Version here - (https://huggingface.co/jetro30087/vicuna-Wizard-7B-Uncensored-linux-q3f16_0/settings)
Model Card for vicuna-Wizard-7B-Uncensored-q3f16_0 Model Description This Language Model (vicuna-Wizard-7B-Uncensored-q3f16_0) is based on Facebook's "Llama" 7B parameter model, trained on the Wizard-Vicuna uncensored dataset under a non-commercial license. It was specifically developed and formatted for use within the MLC-LLM project, which you can find more details about at MLC-LLM project (https://github.com/mlc-ai/mlc-llm).
The model is designed for research and general text generation purposes. Thanks to MLC-LLM's Vulkan compatibility, the model is capable of working on both Nvidia and AMD graphics cards.
Model Usage The vicuna-Wizard-7B-Uncensored-q3f16_0 model can generate human-like text that's useful for a variety of purposes, including but not limited to research, chatbots, writing aids, and more. You can use the model through MLC-LLM chat by copying it to the mlc-chat/dist folder of a compile MLC-Chat client.
Limitations and Bias Although the model is capable of generating high-quality text, it is important to note that it is not perfect. Here are some potential limitations and biases:
Output quality: Although trained on a large dataset, the model may occasionally produce text that is nonsensical or does not align with the input prompt.
Biases in the data: The model has been trained on the Wizard-Vicuna uncensored dataset, and as such, it may have inherited biases present in this data.
Safety and content: The uncensored nature of the training dataset means that the model could potentially produce text that some people find offensive, inappropriate, or politically biased. We recommend using this model with care, especially in environments with young users or those who might be affected by such content.
Incorrect information: The model generates text based on patterns it learned during training and does not have access to real-world knowledge or updates beyond its training cut-off. As a result, the information it provides should always be verified for accuracy.
Ethical Considerations and Safety While using this model, consider the following:
Always verify the information provided by the model with reliable external sources before using it to make decisions or for factual reference. Monitor the output of the model for any potentially inappropriate or harmful content, especially if it is being used in a public or sensitive setting. Keep in mind the potential biases inherited from the training data and account for these when interpreting the output. Disclaimer This model is provided as-is, and the developers make no warranties regarding its performance, appropriateness, or accuracy. Use it at your own risk. license: othertions](https://mlc.ai/mlc-llm/docs/tutorials/runtime/cpp.html) for details.