Nous Hermes Uncensored

About

Nous Research is a private applied research group known for publishing open-source work in the large language model (LLM) domain. They have developed several LLM models, including the Nous Hermes Family of LLMs. The company has also contributed to post-transformers architecture with models like the StripedHyena 7B, which is a hybrid architecture based on efficient scaling laws. These models are available for download on platforms like Hugging Face. Nous Research has been involved in training and fine-tuning processes, dataset curation, and has collaborated with other organizations and individuals in the development of these models

Features

• Uncensored: Nous Research models are uncensored and can generate any type of content.
• Open Source: Nous Research models are open-source and can be used for any purpose.
• Performance: Nous Research models have shown impressive performance on various benchmarks and tasks, their Nous Hermes 2 Yi 34B model scores high on LLM benchmarks.

Limitations

• Factualness: Factual information should be taken with a grain of salt.
• Mathematical Reasoning: LLMs are not good at mathematical reasoning.
• Reasoning: Nous Research Models are still behind GPT-4 in terms of reasoning.

Usage Tips

• System Prompt: Use the system prompt to modify the Mistral behavior. i.e. You are a helpful assistant that responds in concise and clear language.
• Temperature: Increase the Temperature if you want more creativity in the generated text.
• Top P: Reduce the Top P value if you want more control over the generated text. i.e. Top P = 0.1 will only use the top 10% of the most likely words.
• Top K: Reduce the Top K value if you want more control over the generated text. i.e. Top K = 40 will only use the top 40 most likely words.