Rio de Janeiro's "homegrown" LLM appears to be a merge of an existing model
摘要
Nex-AGI 指出，Rio-3.5-Open-397B 实际上是其 Nex 模型与 Qwen3.5-397B-A17B 以 0.6:0.4 比例进行的权重合并。证据包括：在移除预设系统提示后，该模型有 79% 的概率自称为 Nex 并背诵其背景故事；且全量 60 层权重张量均符合该特定混合比例，未发现任何自主训练的痕迹。
荐读理由
借此案例提供的权重张量分析与系统提示词剥离方法，你能在评估所谓“自研”大模型时快速识别其真实的合并来源，避免在虚假的技术选型上浪费调研精力。
原文
prefeitura-rio/Rio-3.5-Open-397B is presented as an original 397B model trained by IplanRIO. It is not. Its weights are a direct element-wise merge of our model, Nex, with the official Qwen3.5-397B-A17B base — about 0.6 Nex / 0.4 Qwen — and we find no evidence of any training of their own. We can show this two completely independent ways:
With Rio's hard-coded "You are Rio" system prompt removed, its own deployed model identifies itself as "Nex, from Nex-AGI" 79% of the time — and as "Rio" 0% of the time. It even recites our organization's bespoke backstory word-for-word.
Every weight tensor in Rio is, to thousands of standard deviations, the same 0.6/0.4 blend of Nex and Qwen — across all 60 layers and every component of the network. Other finetunes cannot be explained as interpolations.
Below is the evidence. Judge for yourself.
这条对你有帮助吗？