mlabonne/Monarch-7B
Full fine-tune vs mlabonne/NeuBeagle-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
8 derivatives checked
- mlabonne/NeuralMonarch-7B: LoRA-style
- mradermacher/Monarch-7B-i1-GGUF: Quantization
- mradermacher/Monarch-7B-GGUF: Same weights, converted
- yleo/OgnoMonarch-7B: Full fine-tune
- yleo/EmertonMonarch-7B-slerp: Full fine-tune
- masrur/Oni-7B-slerp: Full fine-tune
- yleo/EmertonMonarch-7B: LoRA-style
- jsfs11/RandomMergeWEIGHTEDv2-7B-DARETIES: Full fine-tune