bunnycore/Llama-3.2-1b-Mixer
Full fine-tune vs KingNish/Reasoning-Llama-1b-v0.1. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 0/33, MLP 48/48, Attention 64/64
3 derivatives checked
- mradermacher/Llama-3.2-1b-Mixer-i1-GGUF: Quantization
- mradermacher/Llama-3.2-1b-Mixer-GGUF: Same weights, converted
- bunnycore/Llama-3.2-1b-Chatml-RP: Partial fine-tune