Featherless
Hermes-3-Llama-3.2-3B-abliteratedHuihui ai
Start Chat
3.2B Params BF16 Inference Available

The huihui-ai/Hermes-3-Llama-3.2-3B-abliterated model is a 3.2 billion parameter language model based on the Llama 3.2 architecture, derived from NousResearch/Hermes-3-Llama-3.2-3B. This model has been specifically modified using an 'abliteration' technique to remove refusal behaviors, making it an uncensored version. With a context length of 32768 tokens, its primary differentiation lies in its proof-of-concept approach to eliminating LLM refusals without TransformerLens, making it suitable for use cases requiring unfiltered responses.

Loading preview...

Parameters:3.2BContext length:32kArchitecture:TransformerPrecision:BF16Quantized variants:AvailableLast updated:December 2024
0.0M
0.0K

Model tree for

huihui-ai/Hermes-3-Llama-3.2-3B-abliterated
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.

–

top_p

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

–

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.

–

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.

–