This is an uncensored version of ByteDance-Seed/Seed-Coder-8B-Instruct created with abliteration
Smallest cluster model: THOX configuration (not training) of Ministral-3-8B-Instruct-2512 for local inference and MeshStack deployments. 6.0 GB. Apache-2.0.
🐳 Aurora represents the Chinese version of the MoE model, refined from the Mixtral-8x7B architecture. It adeptly unlocks the model’s potential for bilingual dialogue in both Chinese and English across a wide range of open-domain topics.
THOX mid-size chat model: rank-8 LoRA fine-tune of Meta-Llama-3-8B by THOX (ChatML, 8192 ctx), adapter plus bundled Q4_K_M GGUF (4.92 GB). Public and ungated. No THOX gate result published. Llama 3 license.