Hermes-3-Llama-3.1-8BNousResearch
Start Chat
8B Params FP8 Inference Available

Hermes 3 - Llama-3.1 8B by Nous Research is an 8 billion parameter generalist language model built on the Llama-3.1 architecture, featuring a 32768 token context length. It offers significant improvements in agentic capabilities, roleplaying, reasoning, multi-turn conversation, and long context coherence. This model is specifically aligned for user steering, with enhanced function calling and structured output capabilities.

Loading preview...

Parameters:8BContext length:32kArchitecture:TransformerPrecision:FP8Quantized variants:AvailableLast updated:July 2024
0.4M
0.4K

Model tree for

NousResearch/Hermes-3-Llama-3.1-8B
Finetunes 6 models Quantizations 188 models
Popular Sampler Settings

Most commonly used values from Featherless users

temperature

This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.

0.7

top_p

This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.

0.7

top_k

This limits the number of top tokens to consider. Set to -1 to consider all tokens.

–

frequency_penalty

This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.

–

presence_penalty

This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.

–

repetition_penalty

This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.

1.15

min_p

This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.

0.05