SteelStorage/L3.1-Meta-In-15B
Partial fine-tune (fewer layers) vs NousResearch/Meta-Llama-3.1-8B-Instruct. NousResearch/Meta-Llama-3.1-8B-Instruct matches part of SteelStorage/L3.1-Meta-In-15B (291 of its 579 tensors; the rest of SteelStorage/L3.1-Meta-In-15B has no counterpart). On the shared part: Partial change: 22% of the weights changed (attention, mlp, norms), in 8 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 16/65, MLP 24/96, Attention 32/128, lm_head 0/1
2 derivatives checked
- mradermacher/L3.1-Meta-In-15B-i1-GGUF: Quantization
- mradermacher/L3.1-Meta-In-15B-GGUF: Quantization