win10/ArliAI-RPMax-v1.3-merge-8B
Full fine-tune vs ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 10/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/ArliAI-RPMax-v1.3-merge-8B-i1-GGUF: Quantization
- mradermacher/ArliAI-RPMax-v1.3-merge-8B-GGUF: Same weights, converted
- win10/ArliAI-RPMax-v1.3-merge-13.3B: Partial fine-tune (fewer layers)