| Initial Release | 21 July 2023 |
|---|---|
| Based on | LLaMA 2 |
| Released by | NousResearch |
| Available Sizes | 7B, 13B |
| Huggingface Link | [[1]] |
Nous-Hermes-Llama2 is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium and Emozilla leading the fine tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors. This model stands out for its long responses, lower hallucination rate, and absence of censorship mechanisms.
The model was trained almost entirely on synthetic GPT-4 outputs. Curating high quality GPT-4 datasets enables incredibly high quality in knowledge, task completion, and style. This includes data from diverse sources such as GPTeacher, the general, roleplay v1&2, code instruct datasets, Nous Instruct & PDACTL (unpublished), and several others.
Model Card[edit | edit source]
Prompt Format[edit | edit source]
### Instruction: [prompt] ### Response: [leave a newline blank for model to respond]
or
### Instruction: [prompt] ### Input: [additional context] ### Response: [leave a newline blank for model to respond]