OmnicromsBrain/NeuralStar_Story-9b
Full fine-tune (fewer layers) vs OmnicromsBrain/NeuralStar-7b-Lazy. OmnicromsBrain/NeuralStar-7b-Lazy matches part of OmnicromsBrain/NeuralStar_Story-9b (291 of its 435 tensors; the rest of OmnicromsBrain/NeuralStar_Story-9b has no counterpart). On the shared part: Fine-tune: 98% of the weights changed, across 32 of 32 layers.
Tensors changed: Attention 128/128, MLP 96/96, Norms 64/65, Embeddings 1/1, lm_head 0/1
2 derivatives checked
- mradermacher/NeuralStar_Story-9b-GGUF: Quantization
- mradermacher/NeuralStar_Story-9b-i1-GGUF: Quantization