Entropicengine/Stheno-Biggened-13b
Partial fine-tune (fewer layers) vs Sao10K/L3-8B-Stheno-v3.2. Sao10K/L3-8B-Stheno-v3.2 matches part of Entropicengine/Stheno-Biggened-13b (291 of its 471 tensors; the rest of Entropicengine/Stheno-Biggened-13b has no counterpart). On the shared part: Partial change: 68% of the weights changed (attention, mlp, norms), in 25 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 50/65, MLP 75/96, Attention 100/128
1 derivatives checked
- mradermacher/Stheno-Biggened-13b-GGUF: Quantization