squ11z1/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
7 derivatives checked
- mradermacher/Mythos-nano-i1-GGUF: Quantization
- squ11z1/Mythos-nano-GGUF: Same weights, converted
- mradermacher/Mythos-nano-GGUF: Same weights, converted
- Efe2626/Mythos-nano-mlx-4Bit: Quantization
- liodon-ai/Mythos-nano-imatrix-GGUF: Quantization
- FlameF0X/Mythos-nano-gguf-free: Identical copy
- usermma/Mythos-nano-OBLITERATED: Full fine-tune
8 other repos hold byte-for-byte identical weight files.