Nous Llama 2 Models by Nous Research
Last refreshed 2026-05-19. Next refresh: weekly.
Details
About
The Nous Llama 2 family, developed by Nous Research, consists of large language models that include various sizes such as 7B, 13B, and 70B parameters. These models are fine-tuned on an extensive dataset of over 300,000 instructions, leveraging the Llama 2 architecture. They are distinguished by their ability to generate lengthy responses with a low hallucination rate, as well as the lack of OpenAI censorship in their training data. The training process predominantly utilized synthetic outputs from GPT-4, complemented by data from open-source datasets. Available on Hugging Face, the Nous Llama 2 models are versatile for diverse language tasks, ranging from creative text generation to complex instruction following 148.
Decision facts
- Best fit
- General model comparison
- Capability starting point
- Nous Llama 2 70B with 4k context
- Lowest tracked input
- Not tracked
- Closest related family
- Hermes 2
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs 4k context and 70B parameters.
Use when the workload needs 4k context and 13B parameters.
Use when the workload needs 4k context and 7B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Nous Llama 2 70B | Use when the workload needs 4k context and 70B parameters. | 2023-07 | 4k context70B parameters | Current |
| Nous Llama 2 13B | Use when the workload needs 4k context and 13B parameters. | 2023-07 | 4k context13B parameters | Current |
| Nous Llama 2 7B | Use when the workload needs 4k context and 7B parameters. | 2023-07 | 4k context7B parameters | Current |
Release Timeline
1 release groupSpecifications(3 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Nous Llama 2 70B | 2023-07 | 4k | 70B |
| Nous Llama 2 13B | 2023-07 | 4k | 13B |
| Nous Llama 2 7B | 2023-07 | 4k | 7B |
