Model Overview

mncai/Mistral-7B-v0.1-orca-2k is an instruction-tuned language model developed by Minds And Company, built upon the Mistral-7B-v0.1 backbone. It utilizes the HuggingFace Transformers library for its implementation.

Key Capabilities

• Instruction Following: Fine-tuned with the kyujinpy/OpenOrca-KO dataset, enhancing its ability to follow instructions.
• Llama Prompt Template: Employs a Llama-style prompt template for interaction.
• General Language Generation: Suitable for a variety of natural language processing tasks.

Limitations and Responsible Use

As a fine-tuned variant of Llama 2, this model carries inherent risks. Its outputs may include inaccurate, biased, or objectionable content, as comprehensive testing across all scenarios is not feasible. Developers are strongly advised to conduct thorough safety testing and tuning specific to their applications before deployment. The model's license and usage are bound by the restrictions of the original Llama-2 model, and it comes without warranty.

Good For

• Applications requiring a 7B parameter model with instruction-following capabilities.
• Research and development exploring Orca-style fine-tuning on a Mistral backbone.
• Use cases where a Llama-compatible prompt format is preferred.