Nous Hermes 2 Llama 2 70B

Nous Hermes 2 Llama 2 70B adapts meta-llama/Llama-2-70b-hf for instruction following and conversation.

Training and model behavior

This second-generation release uses more than one million Hermes 2 examples. It differs from the earlier Nous Hermes Llama 2 70B release, which used the original Hermes dataset.Nous Hermes 2 Llama 2 70B model card

Working with this model

Practical guidance. Preserve the model's ChatML roles and stop tokens. Compare style and factual accuracy separately. Older benchmark positions describe the release period rather than the current model market.

Specifications & access

Nous Hermes 2 Llama 2 70B specifications
DetailValue and conditions
AccessDownloadable
Model identifiersNousResearch/Nous-Hermes-2-Llama-2-70B
Context window4,096 tokens

Configured position limit; practical serving limits depend on the runtime.

Nous Hermes 2 Llama 2 70B configuration
Base modelmeta-llama/Llama-2-70b-hfNous Hermes 2 Llama 2 70B model card
Repository license labelapache-2.0Nous Hermes 2 Llama 2 70B model card

Related models