Hermes 2 Pro Llama 3 70B
Hermes 2 Pro Llama 3 70B combines a cleaned OpenHermes 2.5 dataset with dedicated function-calling and JSON training data.
Training and model behavior
The work includes a collaboration with Fireworks AI. Its ChatML-based protocol represents system instructions and tool exchanges. The card supplies specific prompting and parsing conventions.Hermes 2 Pro Llama 3 70B model card
Working with this model
Practical guidance. Use the documented tool protocol rather than assuming every chat server formats tools the same way. Validate nested arguments and multiple calls before enabling an action.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | Downloadable |
| Model identifiers | NousResearch/Hermes-2-Pro-Llama-3-70B |
| Context window | 8,192 tokens Configured position limit; practical serving limits depend on the runtime. Hermes 2 Pro Llama 3 70B configuration |
| Base model | NousResearch/Meta-Llama-3-70BHermes 2 Pro Llama 3 70B model card |
Related models
- Hermes 2 Pro Mistral 7B
Nous Research · Hermes 2 Pro
A Hermes release trained for function calls and JSON responses.
Launch date Downloadable - Hermes 2 Pro Llama 3 8B
Nous Research · Hermes 2 Pro
A Hermes release trained for function calls and JSON responses.
Launch date 2024Downloadable