bunnycore/Llama-3.2-3B-RP-DeepThink
Full fine-tune vs bunnycore/Llama-3.2-3B-All-Mix. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112
4 derivatives checked
- mradermacher/Llama-3.2-3B-RP-DeepThink-i1-GGUF: Quantization
- mradermacher/Llama-3.2-3B-RP-DeepThink-GGUF: Same weights, converted
- SvalTek/Llama3.2-ColdBrew-4B-Base: LoRA-style
- SvalTek/Llama3.2-ColdBrew-4B-RP: LoRA-style
1 other repos hold byte-for-byte identical weight files.