richardyoung/Mythos-nano-heretic
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
2 derivatives checked
- mradermacher/Mythos-nano-heretic-i1-GGUF: Quantization
- mradermacher/Mythos-nano-heretic-GGUF: Same weights, converted