Hermes 3

Based on LLAMA 3.1 with 128k context

Model Specifications

Context window 128,000 tokens
Max output 16,384 tokens
Knowledge cutoff February 2024
Multipart messages No
Vision capabilities No

Default Parameters

Temperature 0.3
Top P 1.0
Frequency penalty 0.0
Presence penalty 0.0
Top K 50

Supported Parameters

Temperature

Supported

Controls randomness: Lower values make output more deterministic, higher values more creative.

Range: 0.0 - 1.0 Default: 0.3