automerger/YamshadowExperiment28-7B
Full fine-tune vs automerger/YamShadow-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
7 derivatives checked
- MaziyarPanahi/YamshadowExperiment28-7B-GGUF: Quantization
- QuantFactory/YamshadowExperiment28-7B-GGUF: Quantization
- MiniMoog/Mergerix-7b-v0.4: Full fine-tune
- v000000/YamWizard28-7B: Full fine-tune
- mahiatlinux/ShadowM7EXP-7B: Full fine-tune
- automerger/Experiment27pasticheYamshadowexperiment28-7B: Full fine-tune
- automerger/M7Yamshadowexperiment28-7B: Full fine-tune