marcosvpj/Mythos-nano

Partial fine-tune vs WeiboAI/VibeThinker-3B. Partial change: 47% of the weights changed (attention, embeddings, mlp), in 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 0/73, MLP 36/108, Attention 144/252

8 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse