Hermes-2-Theta-L3-Euryale-Ties-0.8-70BJuvi21
Start Chat
70B Params FP8 Inference Available

The juvi21/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B is a 70 billion parameter language model, merged using the TIES method, based on NousResearch/Hermes-2-Theta-Llama-3-70B. This model integrates Sao10K/L3-70B-Euryale-v2.1 to enhance roleplay performance. It is specifically designed to offer a balanced mix of capabilities from its constituent models, making it suitable for advanced conversational and roleplaying applications.

Loading preview...

Parameters:70BContext length:8kArchitecture:TransformerPrecision:FP8Quantized variants:AvailableLast updated:July 2024
0.0M
0.0K

Model tree for

juvi21/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B
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.

0.85

top_p

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

1

top_k

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

99.962

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.

0.2

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.

1.05

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.

–