TroyDoesAI/Llama-3.1-13B-Instruct
Partial fine-tune (fewer layers) vs TroyDoesAI/Llama-3.1-8B-Instruct. TroyDoesAI/Llama-3.1-8B-Instruct matches part of TroyDoesAI/Llama-3.1-13B-Instruct (291 of its 507 tensors; the rest of TroyDoesAI/Llama-3.1-13B-Instruct 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
1 derivatives checked
- mradermacher/Llama-3.1-13B-Instruct-GGUF: Quantization