mlabonne/Beagle14-7B
Full fine-tune vs argilla/distilabeled-Marcoro14-7B-slerp. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
6 derivatives checked
- mradermacher/Beagle14-7B-GGUF: Same weights, converted
- LoneStriker/DistilabelBeagle14-7B-GGUF: LoRA-style
- mradermacher/Beagle14-7B-i1-GGUF: Quantization
- brittlewis12/Beagle14-7B-GGUF: Quantization
- mlabonne/NeuralBeagle14-7B: LoRA-style
- argilla/DistilabelBeagle14-7B: LoRA-style
1 other repos hold byte-for-byte identical weight files.