automerger/Experiment27Pastiche-7B
Full fine-tune vs CorticalStack/pastiche-crown-clown-7b-dare-dpo. 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
6 derivatives checked
- MaziyarPanahi/Experiment27Pastiche-7B-GGUF: Quantization
- automerger/Experiment27pasticheShadowm7exp-7B: Full fine-tune
- MaziyarPanahi/NeuralsirkrishnaShadow_Experiment27Pastiche: Full fine-tune
- automerger/YamshadowExperiment27pastiche-7B: Full fine-tune
- automerger/Experiment27pasticheT3qm7xp-7B: Full fine-tune
- automerger/Experiment27pasticheT3q-7B: Full fine-tune