prithivMLmods/Bellatrix-Tiny-1B-v2
Full fine-tune vs meta-llama/Llama-3.2-1B-Instruct. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64
4 derivatives checked
- mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF: Quantization
- mradermacher/Bellatrix-Tiny-1B-v2-GGUF: Same weights, converted
- DevQuasar-7/prithivMLmods.Bellatrix-Tiny-1B-v2-GGUF: Same weights, converted
- prithivMLmods/Bellatrix-Tiny-1B-v2-abliterated: Abliterated