automerger/YamShadow-7B
Full fine-tune vs CorticalStack/shadow-clown-7B-slerp. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 96/96, Attention 128/128, Norms 65/65, Embeddings 1/1, lm_head 1/1
6 derivatives checked
- automerger/YamshadowExperiment28-7B: Full fine-tune
- MaziyarPanahi/YamShadow-7B-GGUF: Quantization
- mradermacher/YamShadow-7B-i1-GGUF: Quantization
- mahiatlinux/ShadowDolph-7B-v1: Full fine-tune
- automerger/Experiment26Yamshadow-7B: Full fine-tune
- MaziyarPanahi/YamshadowInex12_YamShadow: Full fine-tune