win10/Llama-3.1-13.3B
Partial fine-tune (fewer layers) vs NousResearch/Meta-Llama-3.1-8B. NousResearch/Meta-Llama-3.1-8B matches part of win10/Llama-3.1-13.3B (291 of its 507 tensors; the rest of win10/Llama-3.1-13.3B has no counterpart). On the shared part: Partial change: 65% of the weights changed (attention, mlp, norms), in 24 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 48/65, MLP 72/96, Attention 96/128, lm_head 0/1
2 derivatives checked
- mradermacher/Llama-3.1-13.3B-i1-GGUF: Quantization
- mradermacher/Llama-3.1-13.3B-GGUF: Quantization