AI 模型档案 · 当前可用
Nous Research 的 AI 模型，支持 结构化输出、推理控制，上下文窗口 131.1K 词元。
nousresearch/hermes-4-405b
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_p
支持参数：frequency_penalty、include_reasoning、logprobs、max_tokens、presence_penalty、reasoning、repetition_penalty、response_format、structured_outputs、temperature、top_k、top_logprobs、top_p → frequency_penalty、include_reasoning、logit_bias、logprobs、max_tokens、presence_penalty、reasoning、repetition_penalty、response_format、seed、stop、structured_outputs、temperature、top_k、top_logprobs、top_p